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. 24-GEMMASCOPE-RES-16K
    6. 2270
    Prev
    Next
    INDEX
    Explanations

    references to specific groups of people or individuals within a context

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

    "Those" followed by a relative pronoun

    np_acts-logits-general · gemini-2.0-flash

    those followed by a description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varandra
    -0.64
    them
    -0.63
     nuages
    -0.63
     pères
    -0.63
    these
    -0.60
     débats
    -0.59
     vœux
    -0.59
    ly
    -0.58
     lèvres
    -0.58
     déclarations
    -0.57
    POSITIVE LOGITS
     who
    1.13
     involved
    0.91
     wishing
    0.80
     closest
    0.78
     seeking
    0.75
     pesky
    0.74
    genen
    0.74
     that
    0.71
     individuals
    0.69
     whom
    0.67
    Activations Density 0.110%

    No Known Activations