© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 5083
    Prev
    Next
    INDEX
    Explanations

    occurrences of opening and closing parentheses and asterisks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >{"
    -0.60
    HasOne
    -0.55
    componentDid
    -0.54
    doors
    -0.53
     doors
    -0.51
    ://"
    -0.51
    himu
    -0.49
    thien
    -0.48
    aupun
    -0.48
     "../../../
    -0.47
    POSITIVE LOGITS
     propOrder
    0.96
     CreateTagHelper
    0.85
    RetentionPolicy
    0.85
    SequentialGroup
    0.75
    󠁣
    0.73
    DotNetBar
    0.71
     AssemblyCulture
    0.69
    PerformLayout
    0.64
    abestanden
    0.64
    ViewChild
    0.62
    Activations Density 0.042%

    No Known Activations