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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7085
    Prev
    Next
    INDEX
    Explanations

    specific names, locations, and events related to legal matters and human activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ecotoxicity
    -0.48
    ayout
    -0.48
     forti
    -0.45
     TIN
    -0.42
     DMSO
    -0.42
     marginBottom
    -0.42
     Longitudinal
    -0.42
    mbggenerated
    -0.41
     Lemon
    -0.41
    Jeografia
    -0.41
    POSITIVE LOGITS
    SharedDtor
    0.49
    angliski
    0.48
    \{\\
    0.47
    ContentLoaded
    0.47
    OGND
    0.46
     altrett
    0.46
    ándola
    0.43
     noDo
    0.43
    principalTable
    0.43
    SpringRunner
    0.42
    Activations Density 2.380%

    No Known Activations