© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15108
    Prev
    Next
    INDEX
    Explanations

    negations and the absence of evidence or claims

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

    "no" followed by "one" or "other"

    np_acts-logits-general · gemini-2.0-flash

    no or not alone

    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
    IUrlHelper
    -0.54
     المعيارى
    -0.49
    IContainer
    -0.48
     elkaar
    -0.42
     ucap
    -0.42
     who
    -0.40
     gynhyrchwyd
    -0.40
     собрать
    -0.40
     που
    -0.40
    tvguidetime
    -0.40
    POSITIVE LOGITS
     AssemblyTitle
    0.95
     Beſ
    0.86
    AccessorTable
    0.77
     مشين
    0.76
    styleType
    0.74
    ChildScrollView
    0.73
     myſelf
    0.73
     defaultstate
    0.72
    MessageOf
    0.71
     portions
    0.70
    Activations Density 0.501%

    No Known Activations