© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2090
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to calibration and measurement inconsistencies

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

    Mitigating errors or unwanted effects

    np_acts-logits-general · gemini-2.0-flash

    minimize contamination or noise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pology
    -0.52
    yelidikan
    -0.48
     fidanz
    -0.47
    ↘
    -0.47
     virgins
    -0.47
    čem
    -0.46
    ConstraintMaker
    -0.45
    ApiOperation
    -0.45
    CREAT
    -0.45
     promessa
    -0.44
    POSITIVE LOGITS
     noise
    0.95
     effects
    0.90
     spurious
    0.88
     interference
    0.85
     errors
    0.83
     inaccuracies
    0.81
     contamin
    0.78
     contributions
    0.78
     effets
    0.77
    noise
    0.77
    Activations Density 2.353%

    No Known Activations