© 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. 2-GEMMASCOPE-RES-16K
    6. 8126
    Prev
    Next
    INDEX
    Explanations

    mentions of living or being alive

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.54
    momile
    -0.48
    IsMutable
    -0.45
     dags
    -0.45
    +#+#
    -0.44
     rotors
    -0.43
    zura
    -0.43
    enoid
    -0.43
    estroyer
    -0.43
    aptors
    -0.43
    POSITIVE LOGITS
     living
    3.11
     live
    2.88
    living
    2.78
     lived
    2.78
    Living
    2.73
     Living
    2.67
     LIVING
    2.56
     Live
    2.45
    Live
    2.42
    LIVING
    2.38
    Activations Density 0.130%

    No Known Activations