© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8860
    Prev
    Next
    INDEX
    Explanations

    references to tools and their functionalities

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

    the word "tool" in technical and programming contexts.

    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
     üzere
    -0.37
     trouw
    -0.36
    NotBlank
    -0.35
    amin
    -0.32
    ا
    -0.31
     admit
    -0.31
    phic
    -0.31
     Blat
    -0.31
    fetchAll
    -0.30
    chriften
    -0.30
    POSITIVE LOGITS
     Tool
    1.00
     tool
    0.96
     TOOL
    0.93
     Tools
    0.90
     tools
    0.88
    Tool
    0.86
    tool
    0.85
    工具
    0.82
    CppMethod
    0.80
     工具
    0.79
    Activations Density 0.077%

    No Known Activations