© 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. 25-GEMMASCOPE-RES-16K
    6. 90
    Prev
    Next
    INDEX
    Explanations

    references to dementia and related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.61
     يتيمه
    -0.59
    EndContext
    -0.58
     kaarangay
    -0.58
     ostavi
    -0.57
    BeginContext
    -0.57
    IntoConstraints
    -0.56
    principalTable
    -0.56
    انيف
    -0.56
    rungsseite
    -0.56
    POSITIVE LOGITS
     F
    3.51
    F
    2.96
     f
    2.19
     getF
    2.01
    getF
    1.96
    f
    1.86
    F
    1.79
     Ф
    1.50
     ف
    1.49
    Fs
    1.23
    Activations Density 1.440%

    No Known Activations