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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12198
    Prev
    Next
    INDEX
    Explanations

    requests and offers communicated through messaging

    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
    RectangleBorder
    -0.68
    AISSEE
    -0.66
    IUrlHelper
    -0.63
    RenderAtEndOf
    -0.59
    =$?
    -0.52
    DrawerToggle
    -0.49
     jdbcTemplate
    -0.49
    haviour
    -0.46
     OFDb
    -0.45
    GOTREF
    -0.44
    POSITIVE LOGITS
    :✨
    0.52
     académica
    0.41
    less
    0.39
    чатый
    0.38
    lone
    0.37
    stato
    0.37
    bottom
    0.37
     persistence
    0.37
    ener
    0.36
    Uns
    0.36
    Activations Density 3.244%

    No Known Activations