© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16503
    Prev
    Next
    INDEX
    Explanations

    sequences of consecutive achievements or performance indicators

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

    consecutive wins or matches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    andExpect
    -0.42
     CURIAM
    -0.41
     fofo
    -0.40
    Попис
    -0.38
     provecho
    -0.38
    ValueGeneration
    -0.37
     comportamiento
    -0.37
    IsPostBack
    -0.36
    StoryboardSegue
    -0.36
    Портали
    -0.36
    POSITIVE LOGITS
    ècie
    0.50
    
    0.49
    providedIn
    0.47
    findpost
    0.44
     متعلقه
    0.44
    lotl
    0.42
     دیکھیے
    0.42
    glGet
    0.42
    fromnode
    0.40
     unbroken
    0.40
    Activations Density 0.022%

    No Known Activations