© 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. 12147
    Prev
    Next
    INDEX
    Explanations

    phrases associated with safety warnings and product liability related to eye protection

    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
    enderror
    -0.65
     Taz
    -0.61
    AndroidJUnit
    -0.59
     Nawaz
    -0.55
     Lacy
    -0.55
    RTDA
    -0.53
    {}{}
    -0.53
     Lei
    -0.52
     Preston
    -0.51
     Koro
    -0.50
    POSITIVE LOGITS
     ph
    2.60
     Ph
    2.52
    Ph
    2.45
     PH
    2.44
     Phi
    2.40
    PH
    2.33
    ph
    2.30
     Phil
    2.30
     phi
    2.29
     PHIL
    2.25
    Activations Density 0.505%

    No Known Activations