© 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. 18-GEMMASCOPE-RES-16K
    11. 6795
    Prev
    Next
    INDEX
    Explanations

    references to applications and tools for managing and organizing tasks or data

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

    preceding actions or functionalities

    np_acts-logits-general · gemini-2.0-flash

    effortless operation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.51
     acred
    -0.48
    ControllerAdvice
    -0.48
     suficientes
    -0.47
     Sufficient
    -0.47
     negativas
    -0.46
    Geplaatst
    -0.45
     necesariamente
    -0.45
     lest
    -0.44
     Públicas
    -0.44
    POSITIVE LOGITS
     seamlessly
    0.93
     instantly
    0.93
     instant
    0.89
     virtual
    0.84
     effortlessly
    0.82
     instantaneously
    0.81
    aarrggbb
    0.80
     Instantly
    0.80
     automatically
    0.79
    instant
    0.78
    Activations Density 0.436%

    No Known Activations