© 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 EvalsExportsinterp-engineNEWAPI 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. 9326
    Prev
    Next
    INDEX
    Explanations

    numerical data and structured annotations

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

    Numbers enclosed in square brackets

    np_acts-logits-general · gemini-2.0-flash

    legal citations and references

    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
     Normdatei
    -0.73
     CanadaChoose
    -0.70
    IsContent
    -0.64
    #+#
    -0.63
     estekak
    -0.62
    
    -0.61
    GEBURTS
    -0.61
    ScopeManager
    -0.60
     '\\;'
    -0.60
    setupUi
    -0.59
    POSITIVE LOGITS
    There
    0.46
    The
    0.46
    This
    0.46
    These
    0.43
    For
    0.42
     medlemmer
    0.42
    TODO
    0.40
    We
    0.39
    If
    0.39
    It
    0.39
    Activations Density 0.639%

    No Known Activations