© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2305
    Prev
    Next
    INDEX
    Explanations

    elements that represent anthology collections or compilations of stories

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

    bibliographic and descriptive information about book collections and anthologies.

    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
     BoxDecoration
    -0.46
     ModelExpression
    -0.45
    FailureListener
    -0.44
     Books
    -0.43
     للاسماء
    -0.43
    Books
    -0.43
     bookstores
    -0.43
     книги
    -0.42
     CreateTagHelper
    -0.42
     AttributeSet
    -0.42
    POSITIVE LOGITS
     short
    1.38
    short
    1.18
    短
    1.12
     Short
    1.02
    Short
    1.02
    ショート
    0.99
     корот
    0.98
     krótk
    0.98
    短い
    0.97
     SHORT
    0.94
    Activations Density 0.452%

    No Known Activations