© 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. 37-GEMMASCOPE-RES-16K
    6. 4143
    Prev
    Next
    INDEX
    Explanations

    content related to consumer decisions and lifestyle activities

    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
    XXXXXXXX
    -0.32
     dancer
    -0.31
     ý
    -0.30
    máquina
    -0.30
    ⚧
    -0.30
     Charger
    -0.29
    følge
    -0.29
    izophren
    -0.29
     проис
    -0.28
    washer
    -0.28
    POSITIVE LOGITS
     sketching
    1.11
     blogging
    1.09
     editing
    1.09
     patching
    1.08
     plotting
    1.08
     campaigning
    1.08
     budgeting
    1.05
     tweeting
    1.03
     interviewing
    1.02
     filming
    1.01
    Activations Density 1.695%

    No Known Activations