© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 5397
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document

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

    Followed by file, is, categories, or dashboard

    np_acts-logits-general · gemini-2.0-flash

    this, Q, annual, dashboard, youth

    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
    ↵↵
    -0.46
    jooq
    -0.40
     (
    -0.39
    <eos>
    -0.38
    trar
    -0.38
    ErrUnexpectedEOF
    -0.38
    世
    -0.38
    UALA
    -0.38
    tgz
    -0.38
    限
    -0.37
    POSITIVE LOGITS
    rungsseite
    0.96
     AssemblyCulture
    0.92
    RectangleBorder
    0.88
    GEBURTSDATUM
    0.85
    Personensuche
    0.79
     snippetHide
    0.78
     hObject
    0.76
    MLLoader
    0.75
     IBOutlet
    0.74
     doInBackground
    0.73
    Activations Density 0.091%

    No Known Activations