© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12899
    Prev
    Next
    INDEX
    Explanations

    references to military actions or drone strikes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.74
    +};
    -0.59
    Hochspringen
    -0.57
    abestanden
    -0.56
    abetes
    -0.56
    -------
    -0.55
    ilités
    -0.54
     OFDb
    -0.53
    PRWEB
    -0.53
    γων
    -0.53
    POSITIVE LOGITS
     attack
    1.81
     attacks
    1.63
    attack
    1.54
     ATTACK
    1.42
     attacked
    1.41
     Attack
    1.37
     attacking
    1.37
     Attacks
    1.31
     attaque
    1.27
    attacks
    1.25
    Activations Density 0.204%

    No Known Activations