© 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. 7-GEMMASCOPE-RES-16K
    6. 12052
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to estimation and quantification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    -0.83
     “
    -0.76
     H
    -0.73
    H
    -0.72
     Ab
    -0.69
     
    -0.69
    “
    -0.68
    </i>
    -0.66
    w
    -0.65
     I
    -0.64
    POSITIVE LOGITS
     estimates
    1.87
     estimate
    1.86
     Estimates
    1.86
     Estimate
    1.83
     ESTIM
    1.75
     estimat
    1.74
    Estimates
    1.72
     Estimated
    1.65
     estimated
    1.64
     estimation
    1.62
    Activations Density 0.149%

    No Known Activations