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. 18-GEMMASCOPE-RES-16K
    6. 14713
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and interactions involving uptake and release

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

    Movement or absorption into something

    np_acts-logits-general · gemini-2.0-flash

    influx, uptake, and release

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.55
    PerformLayout
    -0.53
    winder
    -0.52
    strophy
    -0.51
    irinha
    -0.49
    هل
    -0.49
    MigrationBuilder
    -0.48
    EMPLOY
    -0.48
    jarati
    -0.48
    erializer
    -0.48
    POSITIVE LOGITS
     rates
    0.81
    IsContent
    0.80
     rate
    0.76
    +:+
    0.73
    XmlAccessType
    0.69
    rate
    0.65
    makeConstraints
    0.64
     रेटिंग
    0.63
    rates
    0.62
    WriteBarrier
    0.62
    Activations Density 1.026%

    No Known Activations