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. 2-GEMMASCOPE-RES-16K
    6. 1088
    Prev
    Next
    INDEX
    Explanations

    specific numeric values and certain markup or syntactic elements indicating sections or headings in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rubin
    -0.58
    ypeł
    -0.57
    réhen
    -0.54
    niosek
    -0.51
    FailureListener
    -0.50
    omla
    -0.48
     établi
    -0.47
     FontFamily
    -0.47
    babwe
    -0.46
     paramInt
    -0.46
    POSITIVE LOGITS
    OGND
    0.89
    WithIOException
    0.66
    tvguidetime
    0.63
    UnusedPrivate
    0.63
     SEDS
    0.59
    kuuta
    0.59
    astéroïdes
    0.58
    RunAsync
    0.58
    getOut
    0.57
    subsubsection
    0.55
    Activations Density 0.180%

    No Known Activations