© 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. 2734
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure, particularly around interface and method definitions

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

    interface and method declarations in source code.

    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
     privado
    -0.58
     Private
    -0.57
    Private
    -0.57
     privately
    -0.56
     private
    -0.56
     privées
    -0.52
     PRIVATE
    -0.50
     privé
    -0.50
     privée
    -0.49
     prywat
    -0.49
    POSITIVE LOGITS
     abstract
    0.76
    abstract
    0.65
     abstracts
    0.62
     ModelExpression
    0.60
     abstractions
    0.56
    UIControlState
    0.54
     abstraction
    0.52
     незавершена
    0.52
     abstrak
    0.52
     Abstracts
    0.51
    Activations Density 0.148%

    No Known Activations