© 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. 12-GEMMASCOPE-RES-16K
    11. 3742
    Prev
    Next
    INDEX
    Explanations

    references to backgrounds and background rejection in experimental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GHIJKLM
    -0.56
     MainAxisSize
    -0.51
     belle
    -0.47
    要不
    -0.47
    face
    -0.45
    entier
    -0.44
    eltjes
    -0.44
    umab
    -0.44
    éz
    -0.44
    PREFERRED
    -0.44
    POSITIVE LOGITS
    Hochspringen
    0.72
     InputDecoration
    0.63
     beginnetje
    0.63
     wireType
    0.59
     nahilalakip
    0.59
    aarrggbb
    0.59
     iprot
    0.58
    principalColumn
    0.56
     Taktlose
    0.55
     Roskov
    0.55
    Activations Density 1.088%

    No Known Activations