© 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. 10495
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and testimonies

    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
     vapors
    -0.64
    HEAST
    -0.60
    saraba
    -0.59
    ¯¯
    -0.59
     ComVisible
    -0.57
    تقاوى
    -0.57
    DropColumn
    -0.55
     GetEnumerator
    -0.53
     fichero
    -0.52
    agian
    -0.52
    POSITIVE LOGITS
     Gauteng
    1.23
     Pretoria
    1.20
     Afrikaans
    1.17
     Johannesburg
    1.15
     Durban
    1.11
    🇿
    1.10
     Cape
    1.05
     South
    1.04
    Pty
    1.04
    Afrika
    1.00
    Activations Density 0.329%

    No Known Activations