© 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. 31-GEMMASCOPE-RES-131K
    6. 12357
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or special symbols used in textual representations, particularly the "»" character

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

    continuation and code markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.55
    basicConfig
    -0.50
    SqlClient
    -0.47
    RepeatedField
    -0.44
    jší
    -0.42
     censiti
    -0.42
    Géographie
    -0.41
    くちゃ
    -0.41
     WaitForSeconds
    -0.40
    MessageTagHelper
    -0.40
    POSITIVE LOGITS
    »»
    0.69
     »
    0.63
    ?»
    0.57
    !»
    0.57
    )»
    0.54
    »
    0.53
    .»
    0.53
    »,
    0.53
     («
    0.52
    (">>
    0.51
    Activations Density 0.034%

    No Known Activations