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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 15112
    Prev
    Next
    INDEX
    Explanations

    relative clauses or phrases that specify or modify a noun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aryen
    -0.60
    TabLayout
    -0.57
    ENDIAN
    -0.57
     gắng
    -0.53
    rzez
    -0.53
     QtGui
    -0.53
    Stable
    -0.52
    ddha
    -0.52
    ILLES
    -0.51
    typeorm
    -0.51
    POSITIVE LOGITS
     whereof
    0.99
     waarop
    0.96
     whom
    0.91
     auquel
    0.91
     auxquelles
    0.85
     duquel
    0.81
     whence
    0.78
     Whom
    0.78
     auxquels
    0.77
     which
    0.75
    Activations Density 0.183%

    No Known Activations