© 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. 14402
    Prev
    Next
    INDEX
    Explanations

    references to decisions and choices in various contexts

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

    explanatory or instructional passages that describe processes, procedures, or logical reasoning.

    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
     informée
    -0.59
     pinulongan
    -0.58
     Taktlose
    -0.57
     Normdatei
    -0.56
    intios
    -0.54
    hyrchwyd
    -0.53
    Tikang
    -0.50
    RegressionTest
    -0.50
    __*/
    -0.49
    الإنجليزية
    -0.49
    POSITIVE LOGITS
     it
    2.81
     оно
    2.31
    它
    2.17
     its
    2.03
     Оно
    1.85
     它
    1.68
    它是
    1.67
     Its
    1.67
    它的
    1.60
    มัน
    1.59
    Activations Density 4.198%

    No Known Activations