© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 13640
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "early" in various contexts, particularly in medical and developmental descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ungsver
    -0.48
    zungs
    -0.47
     DbSet
    -0.42
    dallah
    -0.40
    choss
    -0.37
    forhold
    -0.37
     cioccolato
    -0.36
    isDeleted
    -0.36
    的就是
    -0.36
    dct
    -0.36
    POSITIVE LOGITS
     early
    1.81
    early
    1.79
    Early
    1.79
     Early
    1.71
     EARLY
    1.66
    EARLY
    1.60
     frühen
    1.34
     earliest
    1.23
     temprano
    1.23
    早期
    1.19
    Activations Density 0.129%

    No Known Activations