© 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. 3312
    Prev
    Next
    INDEX
    Explanations

    nothing of significance, as no activations were above zero

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

    Follows certain words: Net, Q, R, a, on, Sci

    np_acts-logits-general · gemini-2.0-flash

    mathematical or scientific terms

    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
     betweenstory
    -0.71
    toMatchSnapshot
    -0.70
    rrggbb
    -0.61
    ChildScrollView
    -0.60
    saco
    -0.58
    thenReturn
    -0.52
     Allociné
    -0.52
    Gweler
    -0.51
    adaptiveStyles
    -0.51
    InSection
    -0.51
    POSITIVE LOGITS
     дописавши
    0.74
    ">//
    0.71
     Pingback
    0.71
    Koordinaten
    0.65
    enumii
    0.65
     Disqus
    0.64
     moderator
    0.60
     kasarigan
    0.60
     REPLY
    0.60
    enumi
    0.59
    Activations Density 0.033%

    No Known Activations