© 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. 9-GEMMASCOPE-RES-16K
    11. 9083
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'am' and its variations, which indicate a sense of identity or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.64
    neſs
    -0.53
    ervazione
    -0.46
     OGSÅ
    -0.46
     hina
    -0.46
    leſs
    -0.46
    capace
    -0.45
    Reference
    -0.45
    errated
    -0.45
    øre
    -0.44
    POSITIVE LOGITS
     am
    1.27
     Am
    0.98
    Am
    0.90
    am
    0.64
    Estou
    0.60
     Im
    0.59
     Estou
    0.58
    m
    0.57
     Amm
    0.56
    IAm
    0.55
    Activations Density 0.110%

    No Known Activations