Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10609
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to divisions and distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.76
    aarrggbb
    -0.69
    DebuggerNonUser
    -0.69
    DotNetBar
    -0.64
     PyLong
    -0.63
    __":
    -0.62
    IUrlHelper
    -0.60
    nocache
    -0.59
    ViewFeatures
    -0.58
    ⓧ
    -0.56
    POSITIVE LOGITS
     versus
    0.67
     egentligen
    0.66
     vs
    0.65
    Παραπομπές
    0.57
     next
    0.57
    κτηρισ
    0.57
     poszczegól
    0.57
     compared
    0.56
     дальше
    0.56
    บ้าง
    0.56
    Activations Density 0.515%

    No Known Activations