© 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. 5-GEMMASCOPE-RES-16K
    6. 7054
    Prev
    Next
    INDEX
    Explanations

    roles and contributions related to various processes or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enerbahçe
    -0.48
     bieber
    -0.48
    िया
    -0.47
    enerbah
    -0.47
    éril
    -0.45
     druge
    -0.44
     ensalada
    -0.44
     Esperanto
    -0.43
    志
    -0.43
     materna
    -0.42
    POSITIVE LOGITS
    sizeCache
    1.15
     ModelExpression
    1.13
     role
    0.99
     Role
    0.96
     esternos
    0.96
     محفوظة
    0.90
    Role
    0.88
    الإنجليزية
    0.85
    role
    0.85
    ThroughAttribute
    0.85
    Activations Density 0.429%

    No Known Activations