© 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. 11962
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to scalar products and vector spaces

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

    mathematical terminology related to inner products, scalar products, and vector spaces.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
     يتيمه
    -0.93
    StoryboardSegue
    -0.82
     AssemblyCulture
    -0.80
    KURZBESCHREIBUNG
    -0.80
    SequentialGroup
    -0.74
     AssemblyTitle
    -0.74
    __":
    
    -0.70
    AddTagHelper
    -0.69
    HtmlAttribute
    -0.69
    jsonwebtoken
    -0.69
    POSITIVE LOGITS
     hiér
    0.35
     However
    0.35
     rendszer
    0.35
     by
    0.33
     contraintes
    0.32
     sæ
    0.31
    는데
    0.31
     pourtant
    0.31
     måte
    0.30
     Accesat
    0.29
    Activations Density 0.992%

    No Known Activations