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. 16-GEMMASCOPE-RES-16K
    6. 18
    Prev
    Next
    INDEX
    Explanations

    terms related to examination, treatment, and categorization

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

    preceding nouns related to academic fields

    np_acts-logits-general · gemini-2.0-flash

    subjects of proposals or recommendations

    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
    GraphicsUnit
    -0.97
    SourceChecksum
    -0.82
    yntaxException
    -0.80
     Мексичка
    -0.76
    ConstraintMaker
    -0.76
    AddTagHelper
    -0.73
    StreetMap
    -0.70
    bootstrapcdn
    -0.69
    ViewImports
    -0.69
    SBATCH
    -0.68
    POSITIVE LOGITS
     approach
    0.52
     recommendation
    0.51
    TAWA
    0.49
     proposal
    0.48
    fara
    0.47
     offer
    0.47
    usan
    0.46
     vision
    0.46
     recommendations
    0.46
    のおかげ
    0.45
    Activations Density 0.395%

    No Known Activations