© 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. 22-GEMMASCOPE-RES-16K
    6. 6334
    Prev
    Next
    INDEX
    Explanations

    technical terminology and concepts related to medical and scientific fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houſe
    -0.80
     houſe
    -0.78
     ainfi
    -0.76
     Majefty
    -0.74
     feroit
    -0.71
     pouvoit
    -0.68
     Wikiseite
    -0.66
    ſelves
    -0.66
    ſelf
    -0.65
    erçe
    -0.65
    POSITIVE LOGITS
    neurial
    0.98
    ynthetic
    0.65
    pherical
    0.64
    rical
    0.62
    peutic
    0.61
    pheric
    0.61
    ductory
    0.61
    riotic
    0.61
    ratic
    0.60
    urgical
    0.60
    Activations Density 1.515%

    No Known Activations