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. 20-GEMMASCOPE-RES-16K
    6. 1480
    Prev
    Next
    INDEX
    Explanations

    terms related to databases or programming languages, especially those involving structures and commands

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

    Ending in "nd" and preceding a vowel or consonant

    np_acts-logits-general · gemini-2.0-flash

    words ending in 'ond' or 'ind'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.92
     صوتيه
    -0.91
    antMatchers
    -0.84
     EconPapers
    -0.80
    aarrggbb
    -0.78
    AddTagHelper
    -0.76
    StructEnd
    -0.76
    MemoryWarning
    -0.75
    IntoConstraints
    -0.74
     HasFactory
    -0.74
    POSITIVE LOGITS
    ron
    0.56
    ged
    0.49
    ges
    0.48
    hal
    0.46
    ak
    0.45
    ich
    0.44
     Pers
    0.43
    am
    0.42
    itor
    0.42
    ail
    0.41
    Activations Density 0.233%

    No Known Activations