© 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. 1239
    Prev
    Next
    INDEX
    Explanations

    strings formatted as arrays or lists

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

    Characters appearing inside brackets

    np_acts-logits-general · gemini-2.0-flash

    accessing dictionary keys

    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
    KommentareTeilen
    -0.69
     kasarigan
    -0.66
    adaptiveStyles
    -0.61
    IUrlHelper
    -0.60
    AsUp
    -0.59
     estimés
    -0.57
     ado
    -0.57
    +}$
    -0.56
     calendriers
    -0.55
     المعيارى
    -0.55
    POSITIVE LOGITS
    {{\
    0.97
     Barbier
    0.96
    ["
    0.90
    (["
    0.88
     $[\
    0.83
     ['./
    0.80
    (['
    0.77
    ')['
    0.77
    ['
    0.76
     RIAA
    0.76
    Activations Density 0.201%

    No Known Activations