© 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. 20-GEMMASCOPE-RES-16K
    11. 700
    Prev
    Next
    INDEX
    Explanations

    expressions of human emotions and relationships, particularly those highlighting annoyance or discomfort

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

    words related to personal or family narratives, particularly about age and interpersonal interactions.

    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
    tagHelperRunner
    -0.55
     Gemeinschaft
    -0.35
     примерно
    -0.31
     ucapnya
    -0.30
     relevante
    -0.30
     ý
    -0.30
     Weise
    -0.29
     exactamente
    -0.29
     Geden
    -0.29
     unto
    -0.28
    POSITIVE LOGITS
     Autorizaciones
    0.71
     disambiguazione
    0.68
     ;-)
    0.59
    Autoritní
    0.57
    CppMethod
    0.57
     IBOutlet
    0.57
    ſcher
    0.56
    ⟬
    0.56
    IBOutlet
    0.56
     😉
    0.55
    Activations Density 0.248%

    No Known Activations