© 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. 15-GEMMASCOPE-RES-16K
    11. 1878
    Prev
    Next
    INDEX
    Explanations

    statistical data related to temporal and numeric sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.95
    }}%
    -0.65
     }}}
    -0.59
    //}
    -0.57
    솟
    -0.56
    <?
    -0.55
     vun
    -0.54
    ==$
    -0.53
     k
    -0.53
    }}}{\
    -0.53
    POSITIVE LOGITS
     årene
    0.57
    Décès
    0.56
     consultato
    0.55
    HtmlAttribute
    0.55
    MessageOf
    0.55
    Viitteet
    0.53
    
    0.53
     MenuView
    0.52
    multer
    0.49
    libft
    0.48
    Activations Density 0.111%

    No Known Activations