© 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. 13684
    Prev
    Next
    INDEX
    Explanations

    references to cognitive processes associated with imagination and perception

    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
    enterOuterAlt
    -0.58
     AssemblyCulture
    -0.54
    XDECREF
    -0.47
     ISNI
    -0.46
    AddHtmlAttribute
    -0.45
     optimism
    -0.45
    HtmlAttribute
    -0.45
    الإنجليزية
    -0.44
    новништво
    -0.43
    Optimis
    -0.43
    POSITIVE LOGITS
     meaning
    0.91
     meanings
    0.89
     objects
    0.87
     concepts
    0.78
    meaning
    0.75
     Meaning
    0.72
     reality
    0.71
     symbols
    0.69
     significados
    0.67
    Meaning
    0.67
    Activations Density 0.561%

    No Known Activations