© 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. 4-GEMMASCOPE-RES-16K
    11. 3660
    Prev
    Next
    INDEX
    Explanations

    consecutive numerical sequences or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.80
     rhestr
    -0.78
     Administrativna
    -0.78
     AssemblyVersion
    -0.77
    ])));
    -0.74
     BorderRadius
    -0.73
     nahilalakip
    -0.73
    tagHelperRunner
    -0.73
    apimachinery
    -0.72
    aarrggbb
    -0.71
    POSITIVE LOGITS
    存于互联网档案馆
    0.66
     mendes
    0.46
     כן
    0.45
    Well
    0.44
    旨
    0.44
    باً
    0.43
     I
    0.43
     What
    0.42
    .
    0.41
     tästä
    0.41
    Activations Density 0.132%

    No Known Activations