© 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. 2632
    Prev
    Next
    INDEX
    Explanations

    specific numeric values related to addresses, locations, or quantities

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

    location and address details, particularly street names, building locations, and specific urban geographical references.

    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
     població
    -0.44
     Autorisations
    -0.44
     שוליים
    -0.43
    Atsauces
    -0.43
    קישורים
    -0.42
    tvguidetime
    -0.41
    tanleria
    -0.41
    balleur
    -0.41
    Gale
    -0.40
    wieś
    -0.40
    POSITIVE LOGITS
     downtown
    0.65
     street
    0.64
     Downtown
    0.57
     sidewalk
    0.55
     subway
    0.55
    AnimationsModule
    0.53
    downtown
    0.51
    MethodManager
    0.51
    Downtown
    0.51
     Street
    0.51
    Activations Density 0.171%

    No Known Activations