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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6371
    Prev
    Next
    INDEX
    Explanations

    elements related to conflicts and interests in various languages

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

    Following a language code or determiner

    np_acts-logits-general · gemini-2.0-flash

    Mr. / MR followed by names

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    lée
    -0.52
    annica
    -0.51
    onChangeText
    -0.50
    Бахар
    -0.47
    trise
    -0.46
    <?
    -0.46
    
    -0.45
     مشارکت‌کنندگان
    -0.45
    GINIA
    -0.45
     herself
    -0.45
    POSITIVE LOGITS
     himself
    0.72
    himself
    0.56
     handsome
    0.55
     Councilman
    0.55
    Второй
    0.55
     grandpa
    0.54
     होता
    0.53
     <>",
    0.52
     Himself
    0.51
    ższy
    0.51
    Activations Density 0.222%

    No Known Activations