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. 22-GEMMASCOPE-RES-16K
    6. 12668
    Prev
    Next
    INDEX
    Explanations

    references to the 'Synechocystis' organism or related terms in biological contexts

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

    Tokens starting with "Sy"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Sy

    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
     gratuits
    -0.56
     صوتيه
    -0.54
    addCriterion
    -0.53
    MLLoader
    -0.52
     Off
    -0.50
     libera
    -0.47
     parler
    -0.46
     Phase
    -0.46
     off
    -0.46
     ***!
    -0.45
    POSITIVE LOGITS
     Sy
    0.72
     sy
    0.59
    Sy
    0.58
    setupUi
    0.56
    sy
    0.55
    ="@+
    0.55
    ViewImports
    0.54
     Olympedia
    0.51
    TagHelpers
    0.50
    TabIndex
    0.50
    Activations Density 0.145%

    No Known Activations