© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1805
    Prev
    Next
    INDEX
    Explanations

    text that discusses the persistence of certain themes or entities over time

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

    preceding future tense verbs

    np_acts-logits-general · gemini-2.0-flash

    always, will, find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     am
    -0.50
    umon
    -0.45
     Fe
    -0.45
     Z
    -0.43
     externi
    -0.43
    hta
    -0.42
     E
    -0.42
    erek
    -0.42
     tag
    -0.42
     his
    -0.42
    POSITIVE LOGITS
     ſtill
    0.86
     pleaſure
    0.85
     neceſſ
    0.81
    deauna
    0.81
     poffible
    0.80
     Monfieur
    0.80
     purpoſe
    0.80
    siempre
    0.80
    sempre
    0.79
     raiſ
    0.76
    Activations Density 0.275%

    No Known Activations