© 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. 11432
    Prev
    Next
    INDEX
    Explanations

    information related to environmental themes and survival scenarios

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

    planets or space

    np_acts-logits-general · gemini-2.0-flash

    conquered planets

    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
     يتيمه
    -0.53
    shund
    -0.49
     initComponents
    -0.47
    Бахар
    -0.45
    sizeCache
    -0.43
    issements
    -0.43
    Hyde
    -0.42
     Hyde
    -0.41
    nické
    -0.40
     createStore
    -0.40
    POSITIVE LOGITS
     planets
    1.68
     planet
    1.55
     space
    1.54
     interstellar
    1.52
     galactic
    1.51
     Space
    1.50
     spacecraft
    1.49
     NASA
    1.46
     galaxy
    1.45
     extrater
    1.44
    Activations Density 0.712%

    No Known Activations