Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 12982
    Prev
    Next
    INDEX
    Explanations

    lines of code associated with the definition and implementation of repository classes in a programming context

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

    Code snippets and math expressions

    np_acts-logits-general · gemini-2.0-flash

    arrival byrandom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -1.00
     الحره
    -0.84
    RegressionTest
    -0.81
     كومونز
    -0.77
    principalColumn
    -0.75
    tvguidetime
    -0.74
    abestanden
    -0.74
     Audiodateien
    -0.73
    出版年
    -0.72
     nakalista
    -0.71
    POSITIVE LOGITS
    eral
    0.48
    Personendaten
    0.45
    <eos>
    0.44
    didReceive
    0.40
     pi
    0.38
    孝
    0.37
    arrival
    0.37
    '
    0.37
    mlı
    0.37
    ’
    0.36
    Activations Density 0.008%

    No Known Activations