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. 25-GEMMASCOPE-RES-16K
    6. 15680
    Prev
    Next
    INDEX
    Explanations

    references to media production and distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.31
     Obviously
    -0.29
     barre
    -0.29
     greenish
    -0.28
    obviously
    -0.28
    conv
    -0.28
    uertos
    -0.28
     urma
    -0.26
     obviously
    -0.26
     Por
    -0.26
    POSITIVE LOGITS
     Geiſt
    0.60
     auroit
    0.60
     protoimpl
    0.60
     kasarigan
    0.59
     otomatig
    0.54
     increí
    0.54
    parsedMessage
    0.54
     defaultstate
    0.54
    rungsseite
    0.52
    niſſe
    0.52
    Activations Density 1.121%

    No Known Activations