© 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. 35-GEMMASCOPE-RES-16K
    11. 7255
    Prev
    Next
    INDEX
    Explanations

    content that is classified as offensive or inappropriate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     رع
    -0.35
    ⋱
    -0.32
     semper
    -0.32
    enumi
    -0.32
    GUILayout
    -0.32
    flashdata
    -0.32
     dogged
    -0.31
     sos
    -0.31
    withOpacity
    -0.31
     مهر
    -0.30
    POSITIVE LOGITS
     offensive
    1.17
     nudity
    1.10
     objectionable
    1.07
     explicit
    1.07
     vulgar
    1.05
     obscene
    1.04
    Offensive
    1.02
    offensive
    1.01
     Explicit
    1.01
    Explicit
    1.01
    Activations Density 0.543%

    No Known Activations