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. 2-GEMMASCOPE-RES-16K
    6. 15634
    Prev
    Next
    INDEX
    Explanations

    expressions of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    телна
    -0.58
     нама
    -0.55
    臾
    -0.53
     veren
    -0.53
     образом
    -0.51
     maky
    -0.50
    致
    -0.50
    cile
    -0.49
     hero
    -0.48
    ondheim
    -0.48
    POSITIVE LOGITS
    cplusplus
    0.96
    出版年
    0.94
    uxxxx
    0.93
    ImageContext
    0.90
    ResumeLayout
    0.82
    noinspection
    0.77
     opinion
    0.77
    AndroidJUnit
    0.75
     Ownership
    0.75
    InputBorder
    0.74
    Activations Density 0.102%

    No Known Activations