© 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. 2-GEMMASCOPE-RES-16K
    11. 12839
    Prev
    Next
    INDEX
    Explanations

    terms indicating overall assessments or summaries, especially when referring to frequency or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.69
     ModelRenderer
    -0.68
    sidemargin
    -0.64
    AndEndTag
    -0.58
    Parcelize
    -0.58
    SharedDtor
    -0.57
    twimg
    -0.56
    DBNull
    -0.56
    󠁿
    -0.55
    JspWriter
    -0.54
    POSITIVE LOGITS
     unknown
    0.80
     mouse
    0.73
    mouse
    0.69
     overall
    0.68
    Mouse
    0.68
     Mouse
    0.63
     equivalent
    0.62
     unclear
    0.62
     twice
    0.61
    unknown
    0.61
    Activations Density 0.079%

    No Known Activations