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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14845
    Prev
    Next
    INDEX
    Explanations

    references to specific instances or items in the text

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

    "this" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    referring to preceding nouns

    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
    ragamo
    -0.52
    podes
    -0.52
     Hang
    -0.49
     b
    -0.48
    NavLink
    -0.46
    OfBirth
    -0.44
    HCR
    -0.44
     hang
    -0.42
    ropriate
    -0.42
    barung
    -0.42
    POSITIVE LOGITS
    +#+#
    1.02
    tagHelperRunner
    0.88
    abestanden
    0.77
     poveznice
    0.73
    expandindo
    0.72
    تقاوى
    0.69
    EndContext
    0.69
    Personendaten
    0.68
    SourceChecksum
    0.67
     дописавши
    0.67
    Activations Density 0.472%

    No Known Activations