© 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. 11297
    Prev
    Next
    INDEX
    Explanations

    references to weather modification techniques and their impacts on precipitation

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

    Follows words like "of", "in", "at", "on", "with"

    np_acts-logits-general · gemini-2.0-flash

    numerical modelling, variable selection, regional patterns

    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
    تقاوى
    -0.61
    UnsafeEnabled
    -0.60
    photobucket
    -0.56
    ArgsConstructor
    -0.54
    setVerticalGroup
    -0.54
    ANTLR
    -0.54
    IUrlHelper
    -0.51
    UpInside
    -0.51
    ScopeManager
    -0.49
    mybatisplus
    -0.48
    POSITIVE LOGITS
     climat
    0.70
     Initialized
    0.65
     skillful
    0.65
     hind
    0.63
     skill
    0.63
     forcing
    0.63
     biases
    0.60
     Können
    0.60
     assimilation
    0.59
     initialized
    0.59
    Activations Density 0.528%

    No Known Activations