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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 14255
    Prev
    Next
    INDEX
    Explanations

    sentences that begin with "As", indicating a focus on introductory clauses that provide context or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    truk
    -0.70
     Oedipus
    -0.67
    Enllaços
    -0.66
     useParams
    -0.66
     Jefus
    -0.65
     Fleur
    -0.65
     plebis
    -0.64
     addirittura
    -0.63
     تانيه
    -0.63
    ulity
    -0.63
    POSITIVE LOGITS
     As
    1.52
    As
    1.52
     AS
    0.81
    as
    0.68
    At
    0.66
    GaAs
    0.65
    Towards
    0.65
    wijl
    0.63
    AS
    0.63
    Toward
    0.62
    Activations Density 0.089%

    No Known Activations