© 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. 17-GEMMASCOPE-RES-16K
    6. 5610
    Prev
    Next
    INDEX
    Explanations

    punctuations and mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.61
     a
    -0.60
     to
    -0.59
     in
    -0.58
     at
    -0.58
     
    -0.57
     ...
    -0.55
     (
    -0.54
     men
    -0.53
    :
    -0.52
    POSITIVE LOGITS
     Roskov
    1.29
    tvguidetime
    1.09
    LookAnd
    1.08
    setVerticalGroup
    1.07
    sizeCache
    1.04
     myſelf
    1.02
    WithIOException
    1.02
     betweenstory
    0.99
     ་་
    0.99
    ReusableCell
    0.99
    Activations Density 0.194%

    No Known Activations