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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28092
    Prev
    Next
    INDEX
    Explanations

    information related to quantities and measurement specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dates and colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NUMX
    -1.05
    Personendaten
    -0.91
    \{\\
    -0.85
    verifyException
    -0.79
     beginnetje
    -0.79
    Autoritní
    -0.79
    addCriterion
    -0.78
    ^(@)
    -0.77
    </tfoot>
    -0.77
    "';
    -0.77
    POSITIVE LOGITS
    --
    0.58
    .
    0.57
     –
    0.49
    –
    0.49
     :-
    0.47
     gehalten
    0.47
    :-
    0.46
    R
    0.46
    Never
    0.44
    U
    0.44
    Activations Density 0.181%

    No Known Activations