© 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. 20-GEMMASCOPE-RES-16K
    11. 3630
    Prev
    Next
    INDEX
    Explanations

    structured academic writing, particularly the presentation of research findings and methodologies

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

    academic paper introductory phrases like "In this paper, we present..." or "In this paper, we address...".

    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
     BrowserModule
    -0.57
    tagHelperRunner
    -0.53
    IntoConstraints
    -0.52
     EClass
    -0.50
     يتيمه
    -0.49
    styleType
    -0.49
     autorytatywna
    -0.49
     useParams
    -0.48
    verifyException
    -0.48
     Италијани
    -0.47
    POSITIVE LOGITS
     describes
    0.40
     continuación
    0.39
    WALK
    0.38
     snippetHide
    0.36
     steps
    0.36
     difference
    0.35
     porcelaine
    0.34
     illustrates
    0.34
     inalámbrico
    0.34
     explores
    0.34
    Activations Density 0.522%

    No Known Activations