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. 19-GEMMASCOPE-RES-16K
    6. 2907
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance evaluation and skill assessment in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.79
    DockStyle
    -0.71
     fubject
    -0.67
     purpoſe
    -0.64
     uſ
    -0.63
     ſtate
    -0.62
    "?>
    -0.62
    IsContent
    -0.61
     Jefus
    -0.61
    AnchorStyles
    -0.61
    POSITIVE LOGITS
    +#+
    0.56
    Портал
    0.54
    Modus
    0.53
    ouchable
    0.52
     maybe
    0.52
    OrNull
    0.52
     nube
    0.52
     iprot
    0.51
     betterment
    0.50
     <<<<<<<<<<<<<<
    0.50
    Activations Density 0.329%

    No Known Activations