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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 2619
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names or terms related to individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.92
     surla
    -0.89
     EClass
    -0.85
     насељу
    -0.85
     تضيفلها
    -0.82
    TagMode
    -0.82
    UnusedPrivate
    -0.80
     الرخصة
    -0.80
    GEBURTSDATUM
    -0.77
     ſche
    -0.77
    POSITIVE LOGITS
    ,
    0.47
     Jr
    0.43
    .
    0.40
     and
    0.38
     OMITTED
    0.38
     et
    0.36
    enderror
    0.35
     eds
    0.35
     Preto
    0.32
    opardy
    0.31
    Activations Density 0.142%

    No Known Activations