© 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. 2-GEMMASCOPE-RES-16K
    6. 6051
    Prev
    Next
    INDEX
    Explanations

    terms related to the process of calculating or performing calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GlobalKey
    -0.67
     miR
    -0.60
    #+#
    -0.60
     Yorke
    -0.60
    ridae
    -0.60
     resourceCulture
    -0.59
     ressemb
    -0.59
     thorax
    -0.59
    apiKey
    -0.58
     tocar
    -0.58
    POSITIVE LOGITS
     calculation
    2.70
     calculate
    2.65
     calculations
    2.58
     calculating
    2.50
     Calculate
    2.39
     calculated
    2.39
     Calculation
    2.37
     Calculations
    2.36
     calculates
    2.34
    calculate
    2.32
    Activations Density 0.110%

    No Known Activations