© 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. 28-GEMMASCOPE-RES-16K
    11. 8253
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and responses associated with various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows certain punctuation or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    introducing an explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    due
    -0.63
    Due
    -0.62
     debido
    -0.60
     Due
    -0.60
     due
    -0.58
     DUE
    -0.57
     devido
    -0.56
     vanwege
    -0.55
    DUE
    -0.55
     Aufgrund
    -0.54
    POSITIVE LOGITS
    Personendaten
    0.52
     Biôgrafia
    0.42
     desertcart
    0.41
    SourceChecksum
    0.41
    MessageOf
    0.40
    ViewImports
    0.37
    fizierung
    0.37
     ExecuteAsync
    0.37
    GIVEREF
    0.37
    enterOuterAlt
    0.36
    Activations Density 0.193%

    No Known Activations