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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5778
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "something."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.55
    BagConstraints
    -0.47
    CreateMap
    -0.46
     становника
    -0.46
     userDetails
    -0.45
    ScopeManager
    -0.45
     někter
    -0.45
    charCode
    -0.43
    oredCriteria
    -0.43
     courseId
    -0.42
    POSITIVE LOGITS
     else
    1.19
     ELSE
    0.79
    else
    0.79
    Else
    0.77
     Else
    0.69
     akin
    0.69
     fishy
    0.62
    elif
    0.60
    ELSE
    0.59
     tangible
    0.58
    Activations Density 0.117%

    No Known Activations