© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12302
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming elements related to variable declarations and associated data structures

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

    array or list indexing operations using bracket notation with numeric indices.

    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
    IUrlHelper
    -0.58
    EndGlobalSection
    -0.54
     المعيارى
    -0.52
    IBarButtonItem
    -0.51
    évaluateur
    -0.49
     JpaRepository
    -0.49
     NSError
    -0.48
    userdetails
    -0.48
    stdc
    -0.47
    AnchorStyles
    -0.46
    POSITIVE LOGITS
    lastIndex
    0.47
     indexes
    0.43
     bahía
    0.43
     index
    0.43
    INDEX
    0.42
    0
    0.42
    enfance
    0.42
     jäsen
    0.42
     mukana
    0.42
    msgTypes
    0.42
    Activations Density 0.515%

    No Known Activations