© 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. 8-GEMMASCOPE-RES-16K
    11. 13769
    Prev
    Next
    INDEX
    Explanations

    instances of contradictions or conflicting statements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     versus
    -0.58
     enjeux
    -0.58
    endregion
    -0.55
     vs
    -0.49
     objectForKey
    -0.47
    мах
    -0.47
    simos
    -0.46
    ultuous
    -0.46
    üğü
    -0.46
    estat
    -0.46
    POSITIVE LOGITS
    LookAnd
    0.89
     disambiguazione
    0.88
     Roskov
    0.88
    MigrationBuilder
    0.83
    StructEnd
    0.81
    AddTagHelper
    0.80
     насељу
    0.79
     estekak
    0.78
    webElementXpaths
    0.77
    GEBURTSDATUM
    0.76
    Activations Density 0.042%

    No Known Activations