© 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. 4015
    Prev
    Next
    INDEX
    Explanations

    references to the distinction between reality and fiction

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

    fiction or imagination

    np_acts-logits-general · gemini-2.0-flash

    virtual or imaginary

    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
     AssemblyProduct
    -0.74
    tagHelperRunner
    -0.70
    Tikang
    -0.69
    Tazama
    -0.69
     OkHttpClient
    -0.69
    adpleegd
    -0.68
    ########.
    -0.68
    findpost
    -0.66
    #+#
    -0.66
     pinulongan
    -0.66
    POSITIVE LOGITS
     imaginary
    1.76
     fictional
    1.73
     fictitious
    1.58
    imaginary
    1.54
     fiction
    1.53
     fake
    1.46
     fantasy
    1.44
    Imaginary
    1.41
     imagined
    1.35
     FICTION
    1.35
    Activations Density 0.552%

    No Known Activations