© 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. 4057
    Prev
    Next
    INDEX
    Explanations

    relationships and interpersonal connections, particularly involving love and familial ties

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

    character names and personal pronouns (especially related to gender).

    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
     kulak
    -0.48
     चीज़ों
    -0.46
     насељу
    -0.43
     alternativo
    -0.42
    aderie
    -0.40
     inferiore
    -0.40
     sanctions
    -0.40
    変わ
    -0.38
    domésticos
    -0.38
     chain
    -0.38
    POSITIVE LOGITS
    principalColumn
    0.46
    RTEX
    0.45
    TypedDataSet
    0.43
    帖最后由
    0.43
     Numerade
    0.42
    ImageContext
    0.41
     AssemblyProduct
    0.40
    ItemBackground
    0.40
    classnames
    0.40
     Infórmanos
    0.40
    Activations Density 0.266%

    No Known Activations