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
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 14080
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to soil and environmental research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onPostExecute
    -0.57
    NameInMap
    -0.54
     anything
    -0.54
     semuanya
    -0.54
    providedIn
    -0.54
    esModule
    -0.53
    anything
    -0.52
     tudo
    -0.52
     AssemblyTitle
    -0.51
    InjectAttribute
    -0.50
    POSITIVE LOGITS
     representative
    0.71
     urban
    0.69
     selected
    0.61
     investigated
    0.60
     contemporary
    0.60
     typical
    0.59
     experimentally
    0.57
     studied
    0.57
     Representative
    0.56
    representative
    0.56
    Activations Density 2.241%

    No Known Activations