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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6137
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "excess" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outdoors
    -0.55
    URLException
    -0.53
     AssemblyVersion
    -0.53
    ModelSerializer
    -0.52
    jsonPath
    -0.51
    bootstrapcdn
    -0.49
    WriteLiteral
    -0.49
    NameValuePair
    -0.49
    PYX
    -0.46
    GIVEREF
    -0.46
    POSITIVE LOGITS
     excessive
    0.91
     Excessive
    0.85
     excess
    0.82
    Excessive
    0.82
    excess
    0.77
     Excess
    0.76
    Excess
    0.72
     exceso
    0.65
     fee
    0.59
     excesso
    0.59
    Activations Density 0.051%

    No Known Activations