© 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. 12-GEMMASCOPE-RES-16K
    6. 14448
    Prev
    Next
    INDEX
    Explanations

    text segments discussing actions related to mental and physical health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelves
    -1.19
     iſt
    -1.17
    AddTagHelper
    -1.12
     ſind
    -1.05
     المعيارى
    -1.05
    ſelf
    -1.04
    ^(@)
    -1.03
     Meksiku
    -1.02
     itſelf
    -1.02
     Jefus
    -1.02
    POSITIVE LOGITS
     to
    0.67
     for
    0.59
     of
    0.58
     in
    0.57
    ,
    0.56
    .
    0.54
    ↵↵
    0.53
      
    0.51
    :
    0.51
     nos
    0.50
    Activations Density 0.516%

    No Known Activations