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. 12-GEMMASCOPE-RES-16K
    6. 7902
    Prev
    Next
    INDEX
    Explanations

    assertions or confirmations related to various subjects and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    ている
    -0.68
    <h2>
    -0.67
    eeeeee
    -0.66
    полнитель
    -0.66
     Pembroke
    -0.65
    ITIONAL
    -0.64
    2
    -0.63
     Frankie
    -0.63
    eeee
    -0.62
     Lowe
    -0.62
    POSITIVE LOGITS
    __*/
    0.87
    PMailer
    0.85
     Rashford
    0.84
     natale
    0.81
     Palin
    0.81
     Roskov
    0.81
    Assad
    0.81
    ósito
    0.80
    Personensuche
    0.79
    inflater
    0.78
    Activations Density 0.086%

    No Known Activations