© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 14635
    Prev
    Next
    INDEX
    Explanations

    terms related to support services and resources for victims of violence and emergency situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    24/7 availability

    np_acts-logits-general · gemini-2.0-flash

    24/7 or around the clock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.89
    InitVars
    -0.89
     nahilalakip
    -0.86
     estekak
    -0.82
    IndentedString
    -0.76
     שוליים
    -0.75
     ostavi
    -0.73
    ."));
    -0.73
    fromnode
    -0.73
    exitRule
    -0.73
    POSITIVE LOGITS
     continuous
    0.66
     uninterrupted
    0.57
     nonstop
    0.56
     throughout
    0.55
     sepanjang
    0.54
     ready
    0.53
     Continuous
    0.53
    Continuous
    0.52
    continuous
    0.52
    petual
    0.49
    Activations Density 0.139%

    No Known Activations