© 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. 20-GEMMASCOPE-RES-16K
    6. 6220
    Prev
    Next
    INDEX
    Explanations

    references to specific methods or protocols in research and procedures

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

    technical terms related to procedures and methodological steps in scientific or administrative contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spesies
    -0.51
    Salz
    -0.51
     Ambiental
    -0.50
    Influence
    -0.50
    มอง
    -0.48
     étrangère
    -0.47
    WithMany
    -0.47
    OrWhiteSpace
    -0.47
    canza
    -0.46
     Nuestros
    -0.46
    POSITIVE LOGITS
     procedure
    1.20
     procedures
    1.09
     Procedure
    1.08
    Procedure
    1.00
    procedure
    0.99
     Procedures
    0.96
     PROCEDURE
    0.92
     PROCEDURES
    0.89
    procedures
    0.88
    Procedures
    0.85
    Activations Density 0.050%

    No Known Activations