© 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. 41-GEMMASCOPE-RES-16K
    11. 7597
    Prev
    Next
    INDEX
    Explanations

    references to plans or proposals for projects and improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.52
     resourceCulture
    -0.41
    TypeDefinition
    -0.38
    Parcelize
    -0.38
    haikusbot
    -0.37
    nasse
    -0.36
     fon
    -0.36
     flexion
    -0.35
    Serde
    -0.35
    praš
    -0.35
    POSITIVE LOGITS
     demolish
    0.87
     erect
    0.78
     construct
    0.77
     demolished
    0.74
     install
    0.71
     renovate
    0.70
     tore
    0.67
     bull
    0.67
     exca
    0.65
    construct
    0.65
    Activations Density 0.359%

    No Known Activations