Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 10640
    Prev
    Next
    INDEX
    Explanations

    themes related to the complexity of human relationships and identity

    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
    GEBURTSDATUM
    -0.56
    RegressionTest
    -0.51
    readValue
    -0.51
    MigrationBuilder
    -0.48
    featureID
    -0.44
     illnesses
    -0.44
     sufferings
    -0.44
     Conflicts
    -0.43
     مرئيه
    -0.43
     kasarigan
    -0.42
    POSITIVE LOGITS
     circumstance
    0.72
     possibility
    0.53
     metaphor
    0.52
     anecdote
    0.50
     custom
    0.49
     rumor
    0.47
     precedent
    0.47
     consequence
    0.46
     suggestion
    0.45
     habit
    0.45
    Activations Density 0.561%

    No Known Activations