© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14435
    Prev
    Next
    INDEX
    Explanations

    references to restrictions on weapons, violence, and laws surrounding them

    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
    anskje
    -0.72
     "..\..\..\
    -0.66
    󠁢
    -0.65
     myſelf
    -0.64
     الرياضيه
    -0.63
    atigable
    -0.62
    </tfoot>
    -0.61
    INSEE
    -0.60
    MemoryWarning
    -0.60
    ]")]
    -0.59
    POSITIVE LOGITS
     allowed
    2.47
     permitted
    2.33
     Allowed
    2.15
    allowed
    2.11
    Allowed
    1.94
     ALLOWED
    1.88
    permitted
    1.84
     prohibited
    1.84
     forbidden
    1.81
     permissible
    1.80
    Activations Density 0.607%

    No Known Activations