© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11287
    Prev
    Next
    INDEX
    Explanations

    mentions of "Ganoderma," indicating a focus on a specific type of medicinal mushroom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ActionCreators
    -0.50
     يتيمه
    -0.49
    redirect
    -0.47
    بوابة
    -0.46
    createClass
    -0.45
    poli
    -0.44
    pushFollow
    -0.42
    qai
    -0.42
     POLITICS
    -0.42
     елның
    -0.41
    POSITIVE LOGITS
    $_['
    0.45
    AddTagHelper
    0.44
     GAN
    0.44
     recevez
    0.42
    LookAnd
    0.42
    delwed
    0.41
    endphp
    0.40
     chré
    0.39
    IsMutable
    0.39
     HasFactory
    0.39
    Activations Density 0.189%

    No Known Activations