© 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. 14029
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical values or quantities

    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
    AccessorTable
    -0.79
    NameInMap
    -0.74
    Autoritní
    -0.74
    +#+#
    -0.74
    ItemBackground
    -0.72
    SourceChecksum
    -0.72
     purpoſe
    -0.70
    WithIOException
    -0.69
    MessageOf
    -0.68
    ArgsConstructor
    -0.67
    POSITIVE LOGITS
    MENAFN
    0.39
    SafeMath
    0.38
                
    0.37
    PullParser
    0.37
    </tbody>
    0.36
    法人
    0.35
     straff
    0.34
    endmodule
    0.34
    ഊ
    0.34
    けば
    0.34
    Activations Density 0.040%

    No Known Activations