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. 15-GEMMASCOPE-RES-16K
    6. 2308
    Prev
    Next
    INDEX
    Explanations

    numeric representations and measurements, particularly those related to scientific data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     people
    -0.62
     things
    -0.60
     everyone
    -0.55
    かわ
    -0.55
     someone
    -0.54
     thing
    -0.52
     folks
    -0.52
     nime
    -0.52
     #
    -0.52
     letters
    -0.51
    POSITIVE LOGITS
     estekak
    0.88
    LookAnd
    0.86
     gynhyrchwyd
    0.82
    WithIOException
    0.81
    XmlAccessType
    0.81
     Roskov
    0.81
    setVerticalGroup
    0.80
    DeleteBehavior
    0.80
    VIAF
    0.79
    enumii
    0.79
    Activations Density 0.522%

    No Known Activations