© 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. 11-GEMMASCOPE-RES-16K
    11. 4806
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to programming, specifically SQL and coding specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.68
    expandindo
    -0.55
     стаття
    -0.50
    antMatchers
    -0.50
     Normdatei
    -0.48
    TestingModule
    -0.46
     jspb
    -0.46
    oredCriteria
    -0.46
     SDLK
    -0.45
    RRect
    -0.42
    POSITIVE LOGITS
    Zobacz
    0.40
     inexperienced
    0.40
    gelopen
    0.38
     mijne
    0.37
     ouvriers
    0.37
     obſ
    0.36
    verifyException
    0.36
    mény
    0.36
     professionisti
    0.35
    expliquer
    0.35
    Activations Density 2.194%

    No Known Activations