© 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. 8817
    Prev
    Next
    INDEX
    Explanations

    references to procedures and related terms

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

    after "procedure"

    np_acts-logits-general · gemini-2.0-flash

    procedure following words

    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
    ing
    -2.22
    ING
    -1.55
    ة
    -1.35
    ی
    -1.09
    ingi
    -0.95
    ingan
    -0.89
    ingh
    -0.83
    ς
    -0.82
    ים
    -0.79
    inges
    -0.79
    POSITIVE LOGITS
     latter
    0.95
    abinieri
    0.75
    érience
    0.74
    verwijspagina
    0.74
     Injectable
    0.69
    autorisation
    0.69
    ViewInit
    0.68
    менно
    0.68
    tocks
    0.67
     Cowan
    0.66
    Activations Density 0.808%

    No Known Activations