© 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. 5161
    Prev
    Next
    INDEX
    Explanations

    instances of violence and conflict involving aggressive animals or forces

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

    aggressive or violent confrontations involving animate entities attacking or charging at each other.

    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
     trésor
    -0.39
     dépend
    -0.38
     sustent
    -0.36
     feststellen
    -0.36
     erleben
    -0.36
     wyra
    -0.35
     sustaining
    -0.35
     przyzna
    -0.35
    oa̍t
    -0.35
     Juifs
    -0.35
    POSITIVE LOGITS
     attack
    1.30
     attacks
    1.23
     attacking
    1.22
    attack
    1.09
     attacked
    1.08
     invade
    1.07
     ATTACK
    1.04
    attacks
    1.02
     Attacks
    1.00
     menyerang
    0.99
    Activations Density 0.707%

    No Known Activations