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. 20-GEMMASCOPE-RES-16K
    6. 15588
    Prev
    Next
    INDEX
    Explanations

    references to historical or geographical subjects, particularly related to places and figures in Schleswig-Holstein and surrounding regions

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

    Follows a question or colon

    np_acts-logits-general · gemini-2.0-flash

    citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bénéfices
    -0.60
     -
    -0.55
     even
    -0.54
     nawet
    -0.51
     –
    -0.49
     bienfaits
    -0.49
     benefits
    -0.48
     eficiencia
    -0.47
    DECREF
    -0.47
     addirittura
    -0.47
    POSITIVE LOGITS
    ThroughAttribute
    1.02
    +#+#
    0.96
    脚注の使い方
    0.81
     صوتيه
    0.81
    aarrggbb
    0.78
    DeleteBehavior
    0.78
    IUrlHelper
    0.76
     estekak
    0.74
    AsUp
    0.73
    @[+][
    0.71
    Activations Density 0.211%

    No Known Activations