© 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. 16-GEMMASCOPE-RES-16K
    6. 4773
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to medical and biological research contexts

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

    preceding scientific terms

    np_acts-logits-general · gemini-2.0-flash

    biological and technical terms

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    lgari
    -0.74
    WebControls
    -0.71
     Monfieur
    -0.71
    PasswordEncoder
    -0.70
    quiel
    -0.69
    rrggbb
    -0.66
    RectangleBorder
    -0.65
    crackers
    -0.64
    󠁴
    -0.64
     cerevisiae
    -0.64
    POSITIVE LOGITS
    )$/,
    0.81
    ())));
    0.79
    ())))
    0.74
    ()];
    0.68
    __*/
    0.65
    ')}}
    0.65
    ']));
    0.65
    ()))
    
    0.64
    ')))
    0.64
    )))
    
    0.63
    Activations Density 0.955%

    No Known Activations