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. 14953
    Prev
    Next
    INDEX
    Explanations

    words related to specific technical terms and procedures in scientific contexts

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

    Non-English words/tokens

    np_acts-logits-general · gemini-2.0-flash

    various languages with context

    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
     Shakspeare
    -0.70
     otomatig
    -0.63
    ArgsConstructor
    -0.59
    yntaxException
    -0.58
     elettrica
    -0.57
     termica
    -0.56
     contemporanea
    -0.55
     térmico
    -0.54
     verdadeira
    -0.52
     femininos
    -0.52
    POSITIVE LOGITS
     audio
    0.58
    dillo
    0.58
    prepareStatement
    0.57
    ът
    0.57
    ]='\
    0.57
    ietf
    0.56
    тім
    0.54
    )<\
    0.54
    чатый
    0.53
    การ
    0.52
    Activations Density 0.076%

    No Known Activations