© 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. 14758
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and function definitions

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

    Code snippets and file operations

    np_acts-logits-general · gemini-2.0-flash

    function calls starting with f

    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
     continúas
    -0.80
     rhestr
    -0.74
     onData
    -0.66
     propOrder
    -0.63
    iomanip
    -0.62
    èlement
    -0.61
    исленность
    -0.61
    RetentionPolicy
    -0.61
    endwhile
    -0.61
    Література
    -0.60
    POSITIVE LOGITS
    Спољашње
    0.48
    real
    0.47
     naselje
    0.45
     sn
    0.44
     jorden
    0.42
     كبيرة
    0.41
    Str
    0.41
     bakso
    0.40
     slippers
    0.40
    شهاد
    0.40
    Activations Density 0.397%

    No Known Activations