© 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. 3-GEMMASCOPE-RES-16K
    11. 895
    Prev
    Next
    INDEX
    Explanations

    technical and mathematical notation related to functions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -3.64
    '
    -0.88
    ’
    -0.75
    The
    -0.66
     the
    -0.64
    -
    -0.58
    I
    -0.55
    "
    -0.52
    B
    -0.52
     and
    -0.51
    POSITIVE LOGITS
    ReusableCell
    0.62
    󠁢
    0.62
    igshid
    0.60
    NewLabel
    0.57
     ويكيپ
    0.56
     continuant
    0.56
     مشين
    0.56
    orative
    0.55
    ophone
    0.55
     Tent
    0.55
    Activations Density 28.340%

    No Known Activations