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. 14-GEMMASCOPE-RES-16K
    6. 9743
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to structured environments and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gorithm
    -0.69
    ()")
    -0.69
    ()])
    -0.68
     continuant
    -0.66
     Ανακτήθηκε
    -0.66
    δρ
    -0.64
    ΙΚ
    -0.64
    ?')
    -0.62
    шое
    -0.62
    ']?>
    -0.61
    POSITIVE LOGITS
    yntaxException
    0.77
    InitVars
    0.65
    execSQL
    0.57
    ⟬
    0.55
     ilmiah
    0.55
    getDescriptor
    0.53
     asti
    0.53
     duquel
    0.52
     للمعارف
    0.52
     Bescheid
    0.51
    Activations Density 0.305%

    No Known Activations