© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2763
    Prev
    Next
    INDEX
    Explanations

    terms related to the effectiveness and application of tools and methods in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases describing something as a useful means or tool for accomplishing a purpose.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.41
    (!__
    -0.40
    hoeddwyd
    -0.40
     parseFrom
    -0.39
    ленность
    -0.38
    onedDateTime
    -0.37
     picado
    -0.37
     búsquedas
    -0.36
    zarchiwizowane
    -0.35
     dég
    -0.35
    POSITIVE LOGITS
     tool
    2.14
     tools
    2.02
    tool
    1.80
     herramienta
    1.75
     Tool
    1.72
     outils
    1.68
    工具
    1.68
     Tools
    1.64
    Tool
    1.63
    tools
    1.59
    Activations Density 0.447%

    No Known Activations