Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12502
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their placement in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ((
    -0.63
    ,
    -0.63
     (
    -0.62
    !
    -0.62
     -
    -0.61
     —
    -0.60
    .
    -0.60
     !=
    -0.60
     to
    -0.60
     <
    -0.60
    POSITIVE LOGITS
     itſelf
    1.13
     ་་
    1.05
     $_"
    1.05
    NUMX
    1.05
     ―――――
    1.03
    ſelves
    1.03
    ^(@)
    1.01
     doubtnut
    0.94
     Efq
    0.93
    EDEFAULT
    0.92
    Activations Density 0.683%

    No Known Activations