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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 8332
    Prev
    Next
    INDEX
    Explanations

    expressions related to the concept of holding or grasping

    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
    Vidite
    -0.84
     Италијани
    -0.80
     Roskov
    -0.75
    JspWriter
    -0.68
    новниш
    -0.67
    ----</
    -0.66
     scolaires
    -0.63
     cyclones
    -0.60
     defaultstate
    -0.60
    يكب
    -0.59
    POSITIVE LOGITS
     hold
    1.33
    holds
    1.18
     holds
    1.14
     onto
    1.11
    hold
    1.11
     Hold
    1.10
     HOLD
    1.04
     holding
    1.03
    HOLD
    1.02
     Holds
    1.02
    Activations Density 0.105%

    No Known Activations