Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14642
    Prev
    Next
    INDEX
    Explanations

    names, specifically those related to a person named Jer or variations of that name

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

    starting with "Jer" or "Cher"

    np_acts-logits-general · gemini-2.0-flash

    names starting with Jer or Cher

    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
    findpost
    -1.06
    లాలు
    -0.92
     AssemblyCulture
    -0.90
    RegressionTest
    -0.87
    !("{}",
    -0.86
     Normdatei
    -0.86
    oredCriteria
    -0.85
    ABILIDAD
    -0.85
    awtextra
    -0.85
    OGND
    -0.85
    POSITIVE LOGITS
    er
    0.71
    cher
    0.69
    der
    0.60
     Jer
    0.57
    gor
    0.56
    ed
    0.55
    ker
    0.55
     Yer
    0.55
    Ner
    0.54
    CHER
    0.54
    Activations Density 0.151%

    No Known Activations