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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3730
    Prev
    Next
    INDEX
    Explanations

    concepts related to aging and fertility, particularly in women and how it affects reproductive capabilities

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

    age or aging

    np_acts-logits-general · gemini-2.0-flash

    age and life stage

    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
    ɹ
    -0.40
     makeStyles
    -0.39
    siella
    -0.38
    phylaxis
    -0.38
     agradec
    -0.37
     díl
    -0.36
     heretics
    -0.36
    inheit
    -0.36
     sentito
    -0.36
     paik
    -0.35
    POSITIVE LOGITS
     age
    3.65
     Age
    3.05
     ages
    2.84
    Age
    2.81
     aged
    2.71
     AGE
    2.56
    age
    2.45
     edad
    2.32
     âge
    2.32
     Ages
    2.25
    Activations Density 0.771%

    No Known Activations