© 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. 10-GEMMASCOPE-RES-16K
    11. 15549
    Prev
    Next
    INDEX
    Explanations

    instances of admission or acknowledgment of guilt or involvement in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.66
    ContentAsync
    -0.65
    DockStyle
    -0.64
    majánló
    -0.57
    exitRule
    -0.57
     ſind
    -0.56
    RegistryLite
    -0.55
    Населення
    -0.54
    AnimationsModule
    -0.54
    RectangleBorder
    -0.52
    POSITIVE LOGITS
     admit
    1.41
     admitting
    1.38
     admitted
    1.36
     admits
    1.30
     Admit
    1.24
     admitir
    1.20
     confessed
    1.10
     admiti
    1.07
     confesses
    1.07
     admission
    1.05
    Activations Density 0.371%

    No Known Activations