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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 4521
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to existence and presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kaufman
    -0.46
     voted
    -0.45
    :+:
    -0.42
     Wilkins
    -0.41
    楽しみです
    -0.41
     Weing
    -0.41
     Hydro
    -0.41
    __(/*!
    -0.40
     Designer
    -0.40
    砂
    -0.40
    POSITIVE LOGITS
     presence
    1.03
    presence
    0.97
     existence
    0.94
    Presence
    0.90
     Presence
    0.87
     exist
    0.86
     présence
    0.84
    存在
    0.84
     exists
    0.82
     existencia
    0.79
    Activations Density 0.372%

    No Known Activations