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. 24-GEMMASCOPE-RES-16K
    6. 13785
    Prev
    Next
    INDEX
    Explanations

    common mathematical terms and functions

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

    File paths and code diffs

    np_acts-logits-general · gemini-2.0-flash

    apache commons math python http

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.91
    rupulous
    -0.81
     Monfieur
    -0.79
    <unused28>
    -0.77
    <unused79>
    -0.77
    <unused41>
    -0.77
    <unused80>
    -0.77
    <unused47>
    -0.77
    <unused23>
    -0.77
    <unused43>
    -0.77
    POSITIVE LOGITS
    <unused63>
    0.63
    <unused61>
    0.61
    <unused62>
    0.58
    <unused60>
    0.53
     فريبيس
    0.44
    </h6>
    0.41
    </h5>
    0.40
    …"
    0.40
    </sup>
    0.39
    ...</
    0.39
    Activations Density 0.284%

    No Known Activations