© 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. 39-GEMMASCOPE-RES-16K
    11. 3095
    Prev
    Next
    INDEX
    Explanations

    instances of the word "no."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.81
    findpost
    -0.65
     HasFactory
    -0.64
    routeProvider
    -0.63
     queſta
    -0.63
     ब्रेकडाउन
    -0.62
    EndProject
    -0.60
    WriteTagHelper
    -0.60
    BagConstraints
    -0.59
    참고
    -0.59
    POSITIVE LOGITS
     longer
    0.91
     Longer
    0.52
     doubt
    0.49
    Longer
    0.48
     different
    0.46
    tica
    0.45
     langer
    0.41
    longer
    0.40
     stranger
    0.40
    iser
    0.39
    Activations Density 0.190%

    No Known Activations