© 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. 10341
    Prev
    Next
    INDEX
    Explanations

    concepts related to uniqueness and validation criteria in data handling

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

    "Unique" or related spelling variations occurring in code or text

    np_acts-logits-general · gemini-2.0-flash

    unique / uniqueness

    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
     Eſ
    -0.51
    wiſe
    -0.46
     cauſe
    -0.45
     Reſ
    -0.45
     purpoſe
    -0.44
    سطس
    -0.43
    ñores
    -0.43
     nomina
    -0.42
    ſie
    -0.42
    鱈
    -0.42
    POSITIVE LOGITS
     unique
    3.09
    unique
    2.70
     Unique
    2.63
     uniqueness
    2.61
    Unique
    2.55
     UNIQUE
    2.45
     uniques
    2.33
     unieke
    2.27
     unik
    2.22
     уника
    2.20
    Activations Density 0.582%

    No Known Activations