© 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. 31-GEMMASCOPE-RES-16K
    11. 14942
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "additional" and its variations, as well as related concepts of supplementary information or contributions

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

    the word "additional" appearing at the beginning of sentences or clauses.

    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
    stdc
    -0.44
    #+#
    -0.37
     nærm
    -0.35
     again
    -0.32
     voet
    -0.31
     indeed
    -0.30
     dalej
    -0.30
     vidare
    -0.30
     vorbe
    -0.29
    ostante
    -0.29
    POSITIVE LOGITS
    IsMutable
    0.65
    ymal
    0.63
     سكانية
    0.59
    SBATCH
    0.57
    脚注の使い方
    0.56
     محفوظة
    0.55
     EXTRA
    0.55
     Supplementary
    0.55
    ctable
    0.54
    MessageTagHelper
    0.54
    Activations Density 0.318%

    No Known Activations