© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1839
    Prev
    Next
    INDEX
    Explanations

    instances of the word "big" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words like "big" combined with emotionally charged descriptors or qualifiers.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    adjectives that emphasize largeness or significance, especially “big” used to modify the following noun (and occasionally other size-intensifiers).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "big" when it precedes another word to form a compound or phrase.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageWindow
    -0.46
    actionMode
    -0.42
     apabila
    -0.41
    gemäß
    -0.38
     .
    -0.38
    //}
    -0.38
     Österreich
    -0.38
     metody
    -0.37
     methods
    -0.37
     prestaciones
    -0.37
    POSITIVE LOGITS
     big
    1.30
     BIG
    1.27
    big
    1.20
    Big
    1.20
    BIG
    1.19
     Big
    1.14
     bigger
    1.07
     Biggs
    1.04
    bigger
    1.01
     Bigger
    0.96
    Activations Density 0.063%

    No Known Activations