© 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. 24-GEMMASCOPE-RES-16K
    11. 5887
    Prev
    Next
    INDEX
    Explanations

    actions or processes that involve detection or selection

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

    Misspellings or archaic spellings

    np_acts-logits-general · gemini-2.0-flash

    verb-object relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     however
    -0.31
    …
    -0.30
    ku
    -0.30
    而
    -0.29
     –
    -0.29
     […]
    -0.29
     natomiast
    -0.29
     …
    -0.29
     ...
    -0.28
     THOUGH
    -0.28
    POSITIVE LOGITS
    Datuak
    0.81
    ſelves
    0.71
     myſelf
    0.71
     الحره
    0.71
    Билгалдахарш
    0.71
    ineno
    0.70
    ſelf
    0.69
     ſta
    0.69
    脚注の使い方
    0.67
     increí
    0.66
    Activations Density 0.745%

    No Known Activations