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

    Neuronpedia

    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. 2138
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting cues in the text

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

    Tokens appearing before numbers

    np_acts-logits-general · gemini-2.0-flash

    underscores followed by numbers

    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
     WebDriverWait
    -0.53
    AndEndTag
    -0.53
    BASEPATH
    -0.51
    Glej
    -0.49
    Ecotoxicity
    -0.49
     grade
    -0.48
    Portale
    -0.48
     hoạch
    -0.47
     sockaddr
    -0.46
     lạnh
    -0.46
    POSITIVE LOGITS
    MigrationBuilder
    0.69
    IntoConstraints
    0.66
     pixels
    0.65
     disambiguazione
    0.60
     Infórmanos
    0.58
     متعلقه
    0.57
     Plage
    0.56
     readability
    0.56
     Adriatic
    0.56
     totality
    0.56
    Activations Density 0.143%

    No Known Activations