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. 3443
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with musical performance and achievements in orchestras and competitions

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

    preceding a comma

    np_acts-logits-general · gemini-2.0-flash

    lists of people and orchestras

    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
    <bos>
    -0.92
    ",$
    -0.69
     "..\..\..\
    -0.56
    RoutingModule
    -0.56
    :"-"`
    -0.56
     "..\..\
    -0.55
     \%$,
    -0.54
    ","");
    -0.53
     st
    -0.53
     fur
    -0.53
    POSITIVE LOGITS
    DoubleQuotes
    0.87
     venons
    0.82
     تانيه
    0.82
     متعلقه
    0.77
     تضيفلها
    0.73
     NSCoder
    0.72
    RenderAtEndOf
    0.71
    VersionUID
    0.69
     hunne
    0.68
     zelve
    0.68
    Activations Density 0.442%

    No Known Activations