© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 9248
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to medical conditions and symptoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fahrene
    -0.43
    ={(
    -0.42
    funeralhome
    -0.42
    Alex
    -0.41
    بن
    -0.40
    ː
    -0.40
    舆
    -0.40
     suo
    -0.40
    YT
    -0.40
     Alex
    -0.39
    POSITIVE LOGITS
     comorbidities
    0.89
     health
    0.83
     comor
    0.81
    PerformLayout
    0.77
    ագրություններ
    0.76
    ergies
    0.75
     onPostExecute
    0.75
     الرياضيه
    0.74
     الرخصة
    0.74
    SPATH
    0.73
    Activations Density 0.691%

    No Known Activations