© 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. 24-GEMMASCOPE-RES-16K
    11. 12470
    Prev
    Next
    INDEX
    Explanations

    references to actions, particularly those involving illicit activities or legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "to" followed by a verb of assistance

    np_acts-logits-general · gemini-2.0-flash

    aid or help or support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     χρήση
    -0.69
     Use
    -0.69
    Use
    -0.63
     utilisent
    -0.62
    use
    -0.61
     mať
    -0.59
     use
    -0.58
     useAuth
    -0.56
     StatelessWidget
    -0.55
    serializers
    -0.55
    POSITIVE LOGITS
     aid
    0.94
     help
    0.84
     support
    0.82
     assist
    0.81
     supplement
    0.81
     bolster
    0.77
     complement
    0.74
     enhance
    0.72
     boost
    0.70
     augment
    0.70
    Activations Density 0.347%

    No Known Activations