© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9095
    Prev
    Next
    INDEX
    Explanations

    incidents related to sexual misconduct or assault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.40
    WriteTagHelper
    -0.40
     adelante
    -0.40
    erton
    -0.38
     Merrick
    -0.37
    larger
    -0.37
     표
    -0.37
     larger
    -0.37
     tajam
    -0.36
     thống
    -0.36
    POSITIVE LOGITS
    yntaxException
    0.66
    AndroidJUnit
    0.53
     Meksiku
    0.52
     Numerade
    0.48
    ypep
    0.45
    BagLayout
    0.44
    ImageContext
    0.42
     الرياضيه
    0.42
     дописавши
    0.41
    letoe
    0.40
    Activations Density 0.156%

    No Known Activations