© 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. 37-GEMMASCOPE-RES-16K
    11. 4944
    Prev
    Next
    INDEX
    Explanations

    terms related to "advanced" and its variations, often in a technical or specialized context

    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
    txtName
    -0.38
     excess
    -0.37
    gebung
    -0.37
    InitialState
    -0.36
    imy
    -0.35
     late
    -0.35
    adaptiveStyles
    -0.35
    gänger
    -0.34
     extended
    -0.33
    late
    -0.33
    POSITIVE LOGITS
    addPreferredGap
    0.65
     يتيمه
    0.62
     CreateTagHelper
    0.61
    protoimpl
    0.59
    tagHelperRunner
    0.59
     newBuilder
    0.57
    parsedMessage
    0.51
     stages
    0.50
    RegressionTest
    0.49
    RectangleBorder
    0.49
    Activations Density 0.212%

    No Known Activations