© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 14573
    Prev
    Next
    INDEX
    Explanations

    words that describe intensity or severity, often related to effort or challenge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     höchst
    -0.42
     ringan
    -0.41
    BufferException
    -0.39
     mniej
    -0.38
     nærm
    -0.38
     gorą
    -0.35
     wymiar
    -0.35
     kupić
    -0.34
     Own
    -0.33
     mukaan
    -0.33
    POSITIVE LOGITS
    mindedness
    0.86
     esternos
    0.74
    handed
    0.69
    arming
    0.68
    wiring
    0.67
    -
    0.67
    casted
    0.64
    bearded
    0.64
    sides
    0.63
    SourceChecksum
    0.63
    Activations Density 0.635%

    No Known Activations