© 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. 8976
    Prev
    Next
    INDEX
    Explanations

    elements related to experimental methodology and results in scientific research

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

    Referring to figures or tables

    np_acts-logits-general · gemini-2.0-flash

    in figure references

    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
    GEBURTSDATUM
    -0.67
    ?
    -0.63
    Viitteet
    -0.49
    ?"
    -0.49
    Насе
    -0.47
    Билгалдахарш
    -0.47
    ubov
    -0.46
    canestro
    -0.44
     rec
    -0.44
    espn
    -0.43
    POSITIVE LOGITS
     Figure
    2.35
     Fig
    2.25
    Figure
    2.22
    Fig
    2.15
     Figs
    1.82
     figure
    1.80
    FIGURE
    1.79
    figure
    1.77
     FIGURE
    1.75
     Figures
    1.75
    Activations Density 2.590%

    No Known Activations