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. 17-GEMMASCOPE-RES-16K
    6. 9090
    Prev
    Next
    INDEX
    Explanations

    occurrences of definitions or guidelines related to phases or groups in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ser
    -0.51
     ro
    -0.47
     art
    -0.46
    ViewInit
    -0.46
     om
    -0.42
     pay
    -0.41
     past
    -0.40
     Art
    -0.40
    ikbaar
    -0.40
     ne
    -0.40
    POSITIVE LOGITS
    CppMethod
    1.25
    findpost
    1.01
     defaultstate
    1.01
     surla
    0.97
    httphttps
    0.97
    IndentedString
    0.94
    setVerticalGroup
    0.94
    writeField
    0.93
     الاطلاع
    0.93
     Wikimedijinoj
    0.91
    Activations Density 0.444%

    No Known Activations