© 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. 25-GEMMASCOPE-RES-16K
    11. 2918
    Prev
    Next
    INDEX
    Explanations

    instances of accidental actions or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UVWXYZ
    -0.50
    tament
    -0.48
     règne
    -0.48
    érica
    -0.47
     chêne
    -0.47
    ])]
    -0.47
     radikal
    -0.47
     Emanuel
    -0.46
     Moritz
    -0.45
    󠁧
    -0.45
    POSITIVE LOGITS
     tripped
    1.06
     accidentally
    0.95
     tripping
    0.94
     bumped
    0.93
     accident
    0.84
     fell
    0.83
     spilled
    0.83
     stepped
    0.82
    accident
    0.81
     bumping
    0.80
    Activations Density 0.432%

    No Known Activations