© 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. 18-GEMMASCOPE-RES-16K
    11. 11237
    Prev
    Next
    INDEX
    Explanations

    references to people, their interactions and conversations

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

    Actions involving approaching or running

    np_acts-logits-general · gemini-2.0-flash

    movement towards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getCity
    -0.49
     旧
    -0.48
    mat
    -0.46
     Async
    -0.45
     urban
    -0.45
     samfun
    -0.45
     Urban
    -0.44
     Agency
    -0.44
     fusca
    -0.44
    nthetic
    -0.44
    POSITIVE LOGITS
     approached
    1.03
     approaching
    0.90
    approach
    0.88
     approach
    0.87
     avvic
    0.87
    Approach
    0.86
     approaches
    0.83
     Approach
    0.81
    ConstraintMaker
    0.81
    ValueStyle
    0.79
    Activations Density 0.160%

    No Known Activations