© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14418
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and relationships involving variables and their interactions

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

    Superscript citations

    np_acts-logits-general · gemini-2.0-flash

    closing delimiters like ')}' and '}'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.67
    WebControls
    -0.66
    $(
    -0.64
    BeginContext
    -0.62
     GenerationType
    -0.60
     سكانية
    -0.59
     ExecuteAsync
    -0.58
    Identyfik
    -0.58
     Complaint
    -0.58
    $?
    -0.56
    POSITIVE LOGITS
    )}$
    0.95
    ]}$
    0.86
     \%}$
    0.78
    )}$,
    0.71
     )}$
    0.67
    </sub>
    0.66
    )}$.
    0.65
    })}$
    0.63
    *}$
    0.61
    }$)
    0.58
    Activations Density 0.626%

    No Known Activations