© 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. 5701
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals involved in decision-making or critiques related to justice or governance

    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
     kasarigan
    -0.59
    principalColumn
    -0.56
    tvguidetime
    -0.55
    expandindo
    -0.52
     Signalez
    -0.50
    省市镇
    -0.49
     насељу
    -0.45
    ifflin
    -0.44
    PyExc
    -0.44
    RegressionTest
    -0.43
    POSITIVE LOGITS
     pictured
    0.41
     localObject
    0.40
     screenshot
    0.39
    "][
    0.37
     poster
    0.37
    pictured
    0.37
    photo
    0.36
    Shown
    0.36
    WEBPACK
    0.36
     ké
    0.35
    Activations Density 0.312%

    No Known Activations