© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11788
    Prev
    Next
    INDEX
    Explanations

    words related to attacks or aggressive actions

    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
     zelve
    -0.58
    sidemargin
    -0.54
    Parcelize
    -0.51
     Picchu
    -0.50
     uLocal
    -0.49
     acreditar
    -0.46
     jengibre
    -0.45
     ſein
    -0.44
    deutig
    -0.44
    maakt
    -0.43
    POSITIVE LOGITS
     attack
    1.31
    attack
    1.21
     Attack
    1.13
     ATTACK
    1.06
    Attack
    1.06
     attacks
    1.05
    ATTACK
    0.99
     attacked
    0.96
     attacking
    0.94
    attacks
    0.92
    Activations Density 0.089%

    No Known Activations