© 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. 10128
    Prev
    Next
    INDEX
    Explanations

    terms related to evidence-based practices in various fields

    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
     AssemblyCompany
    -0.79
    EndGlobalSection
    -0.71
    enderror
    -0.69
    SequentialGroup
    -0.69
    findpost
    -0.67
    legged
    -0.66
     HttpNotFound
    -0.66
    tagext
    -0.66
    bearded
    -0.64
    ContentAsync
    -0.64
    POSITIVE LOGITS
     directed
    0.33
     guided
    0.32
     driven
    0.31
    ''');
    0.31
    /*
    0.29
     rather
    0.28
     informed
    0.28
    ícias
    0.27
     inspired
    0.27
    /**
    0.27
    Activations Density 0.586%

    No Known Activations