© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15240
    Prev
    Next
    INDEX
    Explanations

    code elements such as functions or classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -1.71
    httphttps
    -1.65
     CreateTagHelper
    -1.63
    tagHelperRunner
    -1.61
    AddTagHelper
    -1.60
    ArgsConstructor
    -1.60
     lenker
    -1.59
     تضيفلها
    -1.59
    Geplaatst
    -1.56
    expandindo
    -1.54
    POSITIVE LOGITS
     to
    0.20
     in
    0.20
     of
    0.17
     and
    0.16
     as
    0.15
     for
    0.15
     from
    0.15
    to
    0.15
    5
    0.14
    <bos>
    0.13
    Activations Density 0.083%

    No Known Activations