© 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. 9-GEMMASCOPE-RES-131K
    6. 45787
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal experiences and issues

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

    French "le", "un", "menu", "chanel"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.63
     endblock
    -0.53
    kuuta
    -0.51
    kháu
    -0.50
    存于互联网档案馆
    -0.47
     menyus
    -0.47
    tisgarh
    -0.47
     jScrollPane
    -0.46
     GenerationType
    -0.45
     soste
    -0.45
    POSITIVE LOGITS
    TypedDataSet
    0.42
    typeorm
    0.42
    Handlung
    0.40
     Tienen
    0.38
    تفصیلات
    0.37
     tienen
    0.36
    有一
    0.34
     tiene
    0.34
    Vorte
    0.34
     máte
    0.34
    Activations Density 0.020%

    No Known Activations