© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8972
    Prev
    Next
    INDEX
    Explanations

    terms related to semiconductor manufacturing processes

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

    Semiconductor chip manufacturing

    np_acts-logits-general · gemini-2.0-flash

    semiconductor chips and dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.56
    ########.
    -0.54
    racite
    -0.49
     ménage
    -0.47
    romeo
    -0.47
     setuptools
    -0.45
    lja
    -0.45
    ticale
    -0.44
    titura
    -0.43
    Portail
    -0.43
    POSITIVE LOGITS
     chip
    1.37
     semiconductor
    1.37
     semiconductors
    1.23
     Semiconductor
    1.20
     chips
    1.18
    chip
    1.15
     Chip
    1.12
    Chip
    1.11
     Chips
    1.07
    semic
    1.03
    Activations Density 0.399%

    No Known Activations