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. 15691
    Prev
    Next
    INDEX
    Explanations

    strings related to programming syntax and code structure

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

    Non-English language text and code fragments

    np_acts-logits-general · gemini-2.0-flash

    multilingual phrases and sequences

    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
     betreft
    -0.61
    AutoScaleMode
    -0.54
     TestBed
    -0.53
     يتيمه
    -0.51
     raiſ
    -0.49
    uestran
    -0.48
    tvguidetime
    -0.48
     ſhe
    -0.47
     bezoek
    -0.47
     ſta
    -0.47
    POSITIVE LOGITS
     a
    0.68
    MenuInflater
    0.63
     an
    0.63
     sich
    0.62
    PrototypeOf
    0.62
    باً
    0.61
     tot
    0.59
     the
    0.59
    GLenum
    0.57
    leb
    0.57
    Activations Density 0.040%

    No Known Activations