© 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. 21-GEMMASCOPE-RES-16K
    6. 15469
    Prev
    Next
    INDEX
    Explanations

    phrases related to integration and summarizing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.71
    zonder
    -0.59
    CloseOperation
    -0.56
    følge
    -0.54
    usermodel
    -0.53
    foglal
    -0.52
    voorbeeld
    -0.51
    väg
    -0.51
    yaszt
    -0.50
    gelöst
    -0.49
    POSITIVE LOGITS
    hang
    0.63
     pulumi
    0.60
    sp
    0.58
    accompagnement
    0.54
    laying
    0.52
    take
    0.52
    grunt
    0.52
    по
    0.52
     Willen
    0.51
    going
    0.51
    Activations Density 0.043%

    No Known Activations