© 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. 24-GEMMASCOPE-RES-16K
    6. 8027
    Prev
    Next
    INDEX
    Explanations

    references to figures and datasets in the document

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

    Figures with numbers

    np_acts-logits-general · gemini-2.0-flash

    figure numbers and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.83
    hamshire
    -0.78
    المناصب
    -0.78
    +#+
    -0.78
    ]--;
    -0.75
    CodeAttribute
    -0.75
     Chwiliwch
    -0.71
     Normdatei
    -0.70
    ----</
    -0.69
     للمعارف
    -0.67
    POSITIVE LOGITS
     below
    0.68
     shows
    0.66
     illustrates
    0.65
    (
    0.62
     depicts
    0.62
     left
    0.57
    a
    0.55
    below
    0.53
    next
    0.52
     inset
    0.51
    Activations Density 0.646%

    No Known Activations