© 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. 8300
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Main" and its variations within the text

    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
    tagHelperRunner
    -0.69
     Италијани
    -0.59
    EndGlobalSection
    -0.52
     propOrder
    -0.52
    IndentedString
    -0.50
    CppMethod
    -0.49
    InputTagHelper
    -0.43
    fromnode
    -0.41
    complexContent
    -0.41
    autaire
    -0.41
    POSITIVE LOGITS
    tainer
    0.85
    stays
    0.81
    tainers
    0.72
    tains
    0.72
    stream
    0.70
    frame
    0.69
    tained
    0.67
    enance
    0.65
    streaming
    0.64
    AxisAlignment
    0.63
    Activations Density 0.101%

    No Known Activations