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. 5-GEMMASCOPE-RES-16K
    6. 11005
    Prev
    Next
    INDEX
    Explanations

    numerals and decimal points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.61
     appuntamento
    -0.57
     jeito
    -0.55
    multer
    -0.55
    Clik
    -0.54
     odonto
    -0.54
     peur
    -0.53
     innamor
    -0.50
     dinoss
    -0.50
     páss
    -0.49
    POSITIVE LOGITS
    __(/*!
    0.81
    endphp
    0.78
    '">
    0.78
    Datuak
    0.76
    ApiModelProperty
    0.72
     thiệu
    0.72
     _("
    0.72
    最快更新
    0.71
    Referències
    0.70
    原始内容存档于
    0.69
    Activations Density 0.101%

    No Known Activations