© 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. 3-GEMMASCOPE-RES-16K
    11. 9934
    Prev
    Next
    INDEX
    Explanations

    negative symbols and punctuation often related to errors or omissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizePolicy
    -0.71
    دانشنامهٔ
    -0.71
    Hic
    -0.67
    SDAY
    -0.67
    Üdv
    -0.67
    itect
    -0.66
    ſhip
    -0.65
    ンドウ
    -0.65
     GIPHY
    -0.65
    besch
    -0.64
    POSITIVE LOGITS
     -
    2.31
    {-
    1.50
     -"
    1.47
    >-</
    1.45
    ">-
    1.45
     -}
    1.42
     '-
    1.38
    }-
    1.38
    ,-
    1.38
     –
    1.37
    Activations Density 0.628%

    No Known Activations