© 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. 15-GEMMASCOPE-RES-16K
    11. 2175
    Prev
    Next
    INDEX
    Explanations

    elements related to classification and differentiation of legal or systemic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     étoient
    -0.54
    省市镇
    -0.54
    verwijspagina
    -0.53
    AddTagHelper
    -0.50
     ſy
    -0.50
     citoy
    -0.48
     tranſ
    -0.47
     juſ
    -0.47
     étoit
    -0.46
     neceff
    -0.46
    POSITIVE LOGITS
     Ot
    0.36
    aarrggbb
    0.35
     V
    0.35
     Pres
    0.35
     FB
    0.34
    sson
    0.34
     Potter
    0.33
    SharedCtor
    0.33
     Marcos
    0.33
     HF
    0.33
    Activations Density 0.761%

    No Known Activations