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-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43322
    Prev
    Next
    INDEX
    Explanations

    verbs related to making or doing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielle
    -1.13
    ContentAlignment
    -1.12
     houſe
    -1.10
    ChildScrollView
    -1.10
     Jefus
    -1.09
     pleaſure
    -1.09
    IntoConstraints
    -1.08
    rrggbb
    -1.07
     surla
    -1.05
     Chriftian
    -1.00
    POSITIVE LOGITS
     make
    1.34
     made
    1.30
     Make
    1.15
    make
    1.13
    Make
    1.10
     do
    1.10
     makes
    1.09
    made
    1.09
     MAKE
    1.05
     done
    1.02
    Activations Density 0.005%

    No Known Activations