© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3324
    Prev
    Next
    INDEX
    Explanations

    occurrences of class or method definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.60
    tagHelperRunner
    -0.59
    存于互联网档案馆
    -0.57
    InputBorder
    -0.56
     Sandberg
    -0.51
    DECREF
    -0.50
    ſelf
    -0.49
    ⃣
    -0.49
    afficheront
    -0.48
     becauſe
    -0.47
    POSITIVE LOGITS
    ::
    1.90
     ::
    1.27
    >::
    1.22
    :::
    1.16
    ::$
    1.05
    (::
    1.03
    ::::
    1.01
     >::
    0.95
    ::_
    0.95
    ::{
    0.90
    Activations Density 0.063%

    No Known Activations