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. 14-GEMMASCOPE-RES-16K
    6. 4205
    Prev
    Next
    INDEX
    Explanations

    mathematical and technical terms related to machinery and engineering concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.82
     HttpNotFound
    -0.68
    astify
    -0.65
    DotNetBar
    -0.63
     发表于
    -0.63
     snippetHide
    -0.61
     Meksiku
    -0.60
    homonymie
    -0.59
    лтамалар
    -0.59
    lapsingToolbar
    -0.59
    POSITIVE LOGITS
     Paglinawan
    0.55
    OrNull
    0.52
     rağmen
    0.51
    itanie
    0.50
     Allegretto
    0.50
    Referanser
    0.48
    }:${
    0.48
     :')
    0.47
     Untitled
    0.44
    OrEqualTo
    0.44
    Activations Density 7.147%

    No Known Activations