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. 9-GEMMASCOPE-RES-131K
    6. 70393
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands used in document preparation

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

    LaTeX math and document structure

    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
    +#+#
    -0.74
    Derbyniad
    -0.60
     noDo
    -0.60
     Biôgrafia
    -0.58
     betweenstory
    -0.55
    ]")]
    -0.52
    hyrchwyd
    -0.52
    harapkan
    -0.52
    
    -0.50
    InjectAttribute
    -0.49
    POSITIVE LOGITS
    AutoScale
    0.46
    ंदीखरीदारी
    0.42
    center
    0.39
    Center
    0.38
    GTCX
    0.38
    hfill
    0.37
     center
    0.37
     voorzien
    0.36
     the
    0.35
     dati
    0.35
    Activations Density 0.002%

    No Known Activations