© 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. 2074
    Prev
    Next
    INDEX
    Explanations

    quantities and numerical relationships in a context that involves selection or probability

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

    mathematical and computational probability calculations involving multiple letters or numbers.

    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
    IsMutable
    -0.56
     viewDidLoad
    -0.49
    testify
    -0.48
     يتيمه
    -0.48
    TargetException
    -0.46
    wiliwch
    -0.46
    تمبر
    -0.45
    ComponentModel
    -0.44
     TextAppearance
    -0.44
    Beard
    -0.44
    POSITIVE LOGITS
     duo
    0.75
     two
    0.72
     pair
    0.69
     dual
    0.69
    two
    0.68
     twin
    0.67
    TWO
    0.67
    双
    0.65
    Two
    0.65
     dupla
    0.65
    Activations Density 1.027%

    No Known Activations