© 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. 10684
    Prev
    Next
    INDEX
    Explanations

    statements related to accusations or allegations in a political context

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    counting and quantities

    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
     Imp
    -0.52
     Apar
    -0.51
     Clinic
    -0.51
     Kemp
    -0.51
    riae
    -0.49
    mano
    -0.49
    imensional
    -0.49
     Chal
    -0.48
    enderror
    -0.48
     Holt
    -0.47
    POSITIVE LOGITS
     zijne
    0.74
     mijne
    0.69
     avoient
    0.67
     Soyez
    0.66
     ainfi
    0.66
     Şi
    0.66
     asemenea
    0.66
     Monfieur
    0.66
     vocale
    0.64
     propOrder
    0.64
    Activations Density 0.023%

    No Known Activations