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. 128776
    Prev
    Next
    INDEX
    Explanations

    URLs and links to web resources

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

    URLs and retrieval dates

    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
    }$​
    -0.40
     excuses
    -0.36
     userSchema
    -0.34
    >*/
    -0.33
    댑
    -0.33
     노
    -0.32
    chmal
    -0.32
     poor
    -0.31
    aarrggbb
    -0.31
     pobre
    -0.30
    POSITIVE LOGITS
    CrossRef
    0.66
    dostęp
    0.64
    AddTagHelper
    0.60
     Recuperado
    0.55
    msgTypes
    0.55
    RequestMethod
    0.54
     Retrieved
    0.52
    原始内容存档于
    0.52
     bezoek
    0.50
    rawDesc
    0.49
    Activations Density 0.152%

    No Known Activations