© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9484
    Prev
    Next
    INDEX
    Explanations

    concepts related to states and transitions of matter, particularly in scientific contexts

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

    a condition or status

    np_acts-logits-general · gemini-2.0-flash

    quickly, rapidly, via

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Notae
    -0.55
    CloseOperation
    -0.47
     Coming
    -0.47
    "?>
    -0.47
    ]');
    -0.45
    úgó
    -0.45
    ″]
    -0.45
    Coming
    -0.45
    hetta
    -0.44
    ̍t
    -0.43
    POSITIVE LOGITS
     via
    0.60
     rápidamente
    0.59
     quickly
    0.58
     thence
    0.52
     gradually
    0.51
     asap
    0.50
     rapidamente
    0.48
     again
    0.47
     novamente
    0.47
     sooner
    0.46
    Activations Density 0.770%

    No Known Activations