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. 119195
    Prev
    Next
    INDEX
    Explanations

    references to implementation processes or policies

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

    implementing actions or plans

    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
    AccessorTable
    -0.57
    Personensuche
    -0.49
    guisement
    -0.48
    BeforeMethod
    -0.47
     ImportError
    -0.46
     estimés
    -0.46
    NameInMap
    -0.45
    Rüyada
    -0.45
     CreateTagHelper
    -0.44
     besök
    -0.44
    POSITIVE LOGITS
     implementation
    0.94
     Implementation
    0.89
     implementing
    0.89
     Implementing
    0.87
     implement
    0.87
    Implementing
    0.84
    Implementation
    0.80
    implementation
    0.79
     IMPLEMENTATION
    0.78
     Implement
    0.77
    Activations Density 0.055%

    No Known Activations