© 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. 1773
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to public visibility and accessibility

    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
    الحياه
    -0.82
     MainAxisSize
    -0.79
    oneofs
    -0.78
    IndentedString
    -0.71
    󠁢
    -0.68
     BoxFit
    -0.68
    mybatisplus
    -0.67
     actuels
    -0.67
    Hentet
    -0.65
     تضيفلها
    -0.64
    POSITIVE LOGITS
     public
    1.63
     publicly
    1.46
     pública
    1.40
     públicas
    1.35
    Public
    1.34
     PUBLIC
    1.34
    public
    1.32
     Public
    1.30
     publique
    1.20
     publico
    1.19
    Activations Density 0.405%

    No Known Activations