Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5608
    Prev
    Next
    INDEX
    Explanations

    occurrences and discussions of attacks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {~
    -0.74
    Ав
    -0.67
    nO
    -0.65
    ISTRY
    -0.64
     թվական
    -0.62
    ρίου
    -0.61
     whole
    -0.60
     ύ
    -0.59
     км
    -0.59
     beliebt
    -0.58
    POSITIVE LOGITS
     Attack
    1.80
     ATTACK
    1.70
     attack
    1.68
     attacks
    1.63
     Attacks
    1.59
    Attacks
    1.57
    attack
    1.56
    ATTACK
    1.56
    Attack
    1.49
    attacks
    1.48
    Activations Density 0.076%

    No Known Activations