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. 41-GEMMASCOPE-RES-16K
    6. 10470
    Prev
    Next
    INDEX
    Explanations

    terms related to hormonal and sensory influences on behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.46
     ciudadana
    -0.44
     Exacts
    -0.42
     docentes
    -0.39
    \{\\
    -0.39
    orneys
    -0.39
     presidenta
    -0.38
     démission
    -0.38
    ocera
    -0.38
    indows
    -0.36
    POSITIVE LOGITS
     bodybuilding
    0.98
     lifting
    0.84
     hypertrophy
    0.82
     physique
    0.78
     gains
    0.75
     training
    0.75
     lifter
    0.75
     muscle
    0.75
     Muscle
    0.74
     lifts
    0.72
    Activations Density 0.106%

    No Known Activations