© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10386
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to functions and operations

    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>
    -1.06
    Abitanti
    -0.74
    Попис
    -0.72
    ArrowToggle
    -0.71
    presto
    -0.66
     des
    -0.65
    +"/"+
    -0.64
     يتيمه
    -0.64
     cos
    -0.64
    IOS
    -0.63
    POSITIVE LOGITS
     \
    1.13
    \
    0.93
     fédé
    0.80
     écou
    0.77
     nicio
    0.74
     Audiodateien
    0.74
     beliau
    0.72
    ;\
    0.71
     chłop
    0.70
     lèvres
    0.69
    Activations Density 0.106%

    No Known Activations