© 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 EvalsExportsinterp-engineNEWAPI 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. 16192
    Prev
    Next
    INDEX
    Explanations

    technical code structures and syntax elements typical in programming languages

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

    variable names and identifiers in code that appear in conditional comparisons or assignments.

    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
    rungsseite
    -0.74
    IVEREF
    -0.73
    WriteTagHelper
    -0.64
    GEBURTSDATUM
    -0.63
    PyExc
    -0.62
    цездатний
    -0.61
     resourceCulture
    -0.59
    CloseOperation
    -0.58
    脚注の使い方
    -0.58
    IUrlHelper
    -0.57
    POSITIVE LOGITS
     might
    0.45
     ==
    0.45
     similarly
    0.41
    spyOn
    0.37
     >=
    0.36
     ブレスレット
    0.36
     <=
    0.35
     !=
    0.35
     else
    0.34
    ächlich
    0.34
    Activations Density 0.409%

    No Known Activations