© 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. 21-GEMMASCOPE-RES-16K
    11. 6316
    Prev
    Next
    INDEX
    Explanations

    terms related to estimations and approximations of values or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oporosis
    -0.51
     identified
    -0.50
    </i>
    -0.50
    smith
    -0.50
    </b>
    -0.50
    мам
    -0.49
    UObject
    -0.49
    station
    -0.47
    schlag
    -0.46
    ness
    -0.46
    POSITIVE LOGITS
    timate
    0.90
     Roskov
    0.86
    Personensuche
    0.80
    IMATE
    0.80
     GenerationType
    0.78
     Himo
    0.72
     iſt
    0.71
    
    0.71
    ]")]
    0.69
    titleMargin
    0.68
    Activations Density 0.133%

    No Known Activations