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. 14690
    Prev
    Next
    INDEX
    Explanations

    definitive articles such as "the" and possessive pronouns like "my" and "his"

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

    "The" preceding specific nouns

    np_acts-logits-general · gemini-2.0-flash

    the followed by specific noun

    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
     impactful
    -0.79
     demographics
    -0.71
     Kontext
    -0.69
     onboarding
    -0.68
     seamlessly
    -0.68
     standalone
    -0.67
     playbook
    -0.66
    logías
    -0.65
     customizable
    -0.65
    เยอะ
    -0.64
    POSITIVE LOGITS
    faßt
    0.82
     muß
    0.76
    principalColumn
    0.70
    luß
    0.68
     daß
    0.68
    laß
    0.67
     läßt
    0.65
    reportWebVitals
    0.64
     NgModule
    0.63
     immédi
    0.61
    Activations Density 0.600%

    No Known Activations