© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8449
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to influence functions and statistical analysis in the context of modeling and estimation

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

    technical and mathematical terminology related to statistical analysis and correlation functions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.53
    MathML
    -0.43
    zogen
    -0.41
     Numerade
    -0.40
    お願いします
    -0.38
     contigo
    -0.37
    wy
    -0.36
     sĩ
    -0.36
     вы
    -0.36
    ьаж
    -0.35
    POSITIVE LOGITS
     theorems
    0.57
     analysis
    0.57
     theory
    0.56
    +#+#
    0.56
     ujednoznacz
    0.55
     criter
    0.54
    Espèce
    0.52
    crollView
    0.51
     analyses
    0.51
     model
    0.50
    Activations Density 2.236%

    No Known Activations