© 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. 812
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to cultural references and organizations

    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
     يتيمه
    -0.72
    SceneManagement
    -0.56
     Poincar
    -0.55
    DockStyle
    -0.52
    principalColumn
    -0.52
     createSprite
    -0.50
     nahilalakip
    -0.49
    ViewFeatures
    -0.49
     quantization
    -0.48
     насељу
    -0.48
    POSITIVE LOGITS
     fieltro
    0.52
     aquarela
    0.51
     laikā
    0.49
     quæ
    0.49
     lèvres
    0.49
     alluminio
    0.49
     ganchillo
    0.49
    näm
    0.48
     cucchia
    0.48
     morire
    0.48
    Activations Density 0.023%

    No Known Activations