© 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. 7145
    Prev
    Next
    INDEX
    Explanations

    key terms related to decision-making processes

    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
    ThroughAttribute
    -0.60
    Obrázky
    -0.54
    RegressionTest
    -0.50
    StoryboardSegue
    -0.47
     resourceCulture
    -0.47
    ExtendWith
    -0.46
    principalColumn
    -0.45
    Referencie
    -0.44
    RenderAtEndOf
    -0.42
     jadx
    -0.41
    POSITIVE LOGITS
     make
    3.05
     making
    3.00
    make
    2.88
     Make
    2.75
     Making
    2.73
    Making
    2.72
    Make
    2.72
    making
    2.66
     makes
    2.64
     MAKE
    2.55
    Activations Density 3.640%

    No Known Activations