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. 34-GEMMASCOPE-RES-16K
    6. 11617
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical disabilities and impairments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.32
     kasarigan
    -0.31
     hinweg
    -0.31
     renovables
    -0.30
     spot
    -0.30
     organizaciones
    -0.29
     gratuites
    -0.29
     geschehen
    -0.29
    áneo
    -0.29
     arché
    -0.29
    POSITIVE LOGITS
     Activities
    0.82
     mobility
    0.79
    Activities
    0.77
     Mobility
    0.73
     walking
    0.72
    activities
    0.71
    mobility
    0.71
    ADL
    0.71
     functional
    0.70
    Mobility
    0.70
    Activations Density 0.504%

    No Known Activations