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. 22-GEMMASCOPE-RES-16K
    6. 3576
    Prev
    Next
    INDEX
    Explanations

    dates and times related to events or records

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

    Dates with year

    np_acts-logits-general · gemini-2.0-flash

    dates and legal filings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.68
    SuppressMessage
    -0.66
     AssemblyTitle
    -0.63
    fastjson
    -0.56
    /**
    -0.54
    ::_('
    -0.52
    indd
    -0.51
    stdc
    -0.49
    laquo
    -0.49
    netty
    -0.49
    POSITIVE LOGITS
    fjspx
    0.65
    ühner
    0.62
    #+#
    0.62
    delwed
    0.58
     Roskov
    0.55
    bleven
    0.54
    setVerticalGroup
    0.54
    8
    0.54
    RenderAtEndOf
    0.53
     Kraw
    0.53
    Activations Density 0.109%

    No Known Activations