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. 7-GEMMASCOPE-RES-16K
    6. 7170
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and statistical standards or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ücks
    -0.51
    mpre
    -0.49
     Catawiki
    -0.49
     shi
    -0.48
    eloma
    -0.48
    這一
    -0.48
    ambique
    -0.47
    konos
    -0.46
    NSON
    -0.46
     hoeveel
    -0.45
    POSITIVE LOGITS
    GraphicsUnit
    1.29
    ImageContext
    1.08
     GenerationType
    1.08
    GenerationType
    1.04
     مرئيه
    1.01
     CreateTagHelper
    0.95
     '\\;'
    0.93
     beginnetje
    0.88
    PyExc
    0.88
     consultato
    0.87
    Activations Density 1.445%

    No Known Activations