© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1897
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to coefficients and their properties

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

    Mentioning "coefficients."

    np_acts-logits-general · gemini-2.0-flash

    integer coefficients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.60
     HasFactory
    -0.59
     чел
    -0.56
    ietf
    -0.54
     createSlice
    -0.54
    المكان
    -0.51
     Monark
    -0.49
    rucks
    -0.48
    #+#
    -0.48
    asonic
    -0.48
    POSITIVE LOGITS
     coefficients
    1.27
     coefficient
    1.06
     Coefficients
    1.02
     Coefficient
    0.87
    coefficient
    0.83
    coefficients
    0.83
    系数
    0.78
     coeff
    0.76
    Coefficient
    0.73
     coef
    0.69
    Activations Density 1.743%

    No Known Activations