© 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. 605
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data types and functions

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

    C++ and other programming language syntax elements, particularly type declarations, template syntax, and pointer/reference operators.

    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
    AsUp
    -0.71
    ViewFeatures
    -0.57
    AddTagHelper
    -0.56
    PMailer
    -0.54
    tinyos
    -0.53
     فريبيس
    -0.50
    msgTypes
    -0.50
     Commencez
    -0.49
    __(/*!
    -0.49
    WireFormatLite
    -0.47
    POSITIVE LOGITS
     result
    0.48
     A
    0.46
     x
    0.44
     temp
    0.43
    mylist
    0.42
     answer
    0.40
     ans
    0.40
     X
    0.40
     fruit
    0.38
    result
    0.37
    Activations Density 0.388%

    No Known Activations