Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 35820
    Prev
    Next
    INDEX
    Explanations

    patterns or sequences in data, possibly related to structure or formatting

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

    following continuation marks

    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
    OGND
    -0.81
    Autoritní
    -0.73
    UserScript
    -0.73
     للاسماء
    -0.72
     nonUne
    -0.69
     tartalomajánló
    -0.68
     pleaſure
    -0.67
     purpoſe
    -0.66
    KURZBESCHREIBUNG
    -0.65
    ंदीखरीदारी
    -0.64
    POSITIVE LOGITS
    esterno
    0.36
     εκ
    0.36
     Ne
    0.36
     Denken
    0.35
     contemporánea
    0.35
    Mutex
    0.34
     again
    0.34
     onder
    0.34
     contemporaine
    0.33
    сно
    0.33
    Activations Density 0.010%

    No Known Activations