Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 576
    Prev
    Next
    INDEX
    Explanations

    scenes involving movement, particularly of people or animals in a social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.60
    principalColumn
    -0.53
     pasaj
    -0.48
     relâche
    -0.47
    Portail
    -0.46
    Personensuche
    -0.45
    ContentLoaded
    -0.45
    smithy
    -0.43
    ⓧ
    -0.43
     vane
    -0.43
    POSITIVE LOGITS
     approached
    1.20
     approaching
    1.15
     approach
    1.12
     approaches
    1.11
     avvic
    1.06
     acercarse
    1.06
    approach
    1.05
    appro
    1.00
     Approach
    0.98
     APPROACH
    0.98
    Activations Density 0.197%

    No Known Activations