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. 13-GEMMASCOPE-RES-16K
    6. 6063
    Prev
    Next
    INDEX
    Explanations

    strings related to GPU device and computation configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     call
    -0.46
     base
    -0.46
     may
    -0.45
    ato
    -0.45
     might
    -0.43
     p
    -0.43
     chi
    -0.43
     Chi
    -0.43
    may
    -0.43
     video
    -0.42
    POSITIVE LOGITS
     resourceCulture
    1.31
    mybatisplus
    1.02
     reaſon
    0.99
     myſelf
    0.98
    AsUp
    0.97
    IntoConstraints
    0.96
     purpoſe
    0.94
    initComponents
    0.93
     ſtate
    0.91
     Efq
    0.90
    Activations Density 0.194%

    No Known Activations