Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7875
    Prev
    Next
    INDEX
    Explanations

    connections between adaptive genetics and environmental factors

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

    Seasonally variable selection and adaptation

    np_acts-logits-general · gemini-2.0-flash

    seasonal selection pressures

    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
    DockStyle
    -0.58
     déput
    -0.56
     CommonModule
    -0.54
     ExecuteAsync
    -0.52
    tuous
    -0.51
     uuidv
    -0.50
    NewReader
    -0.50
     AudioSource
    -0.49
    thigh
    -0.49
    InjectAttribute
    -0.49
    POSITIVE LOGITS
     ecological
    0.74
     ecologically
    0.71
     mortality
    0.64
     ökolog
    0.62
    ecological
    0.62
    SBATCH
    0.60
     Ecological
    0.59
     spatial
    0.59
     ecology
    0.56
     sensu
    0.56
    Activations Density 1.615%

    No Known Activations