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. 8-GEMMASCOPE-RES-16K
    6. 15189
    Prev
    Next
    INDEX
    Explanations

    the presence of specific system identifiers or metadata in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.83
    tagHelperRunner
    -0.80
    SequentialGroup
    -0.77
     CascadeType
    -0.76
    esgue
    -0.71
    uxxxx
    -0.71
    GraphicsUnit
    -0.69
    ########.
    -0.69
     виправивши
    -0.69
     transfieras
    -0.67
    POSITIVE LOGITS
    Portail
    0.57
    ↵↵
    0.46
     anglès
    0.45
    んぼ
    0.44
    UIColor
    0.43
     dolayı
    0.42
     veda
    0.42
    ricle
    0.42
     lamella
    0.42
    illeur
    0.41
    Activations Density 0.718%

    No Known Activations