© 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-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2204
    Prev
    Next
    INDEX
    Explanations

    references to safety and security systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.54
     Meksiku
    -0.51
    ंदीखरीदारी
    -0.48
    hithe
    -0.46
    verifyException
    -0.45
    capped
    -0.43
    󠁣
    -0.43
    otry
    -0.43
     capped
    -0.42
     Strips
    -0.42
    POSITIVE LOGITS
     ſche
    0.47
     ſtate
    0.45
     forskning
    0.44
     employees
    0.43
     houſe
    0.43
     matéri
    0.42
     leal
    0.42
    Specifiche
    0.42
     stiefel
    0.41
     samfun
    0.41
    Activations Density 0.473%

    No Known Activations