© 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. 4-GEMMASCOPE-RES-16K
    6. 2931
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly sentences ending with periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    intervento
    -0.71
    arrol
    -0.71
    BagConstraints
    -0.69
    parametros
    -0.69
    ments
    -0.69
    pośred
    -0.69
    ïs
    -0.69
    hyd
    -0.68
    gebob
    -0.68
    impianto
    -0.68
    POSITIVE LOGITS
    。
    1.59
    )。
    1.06
     。
    1.03
    ।
    1.00
    )。
    0.94
    ="/">
    0.94
    __':
    0.89
    .。
    0.87
    %。
    0.86
     cune
    0.85
    Activations Density 0.068%

    No Known Activations