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 - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1111
    Prev
    Next
    INDEX
    Explanations

    phrases involving spoken or written statements, especially those that make strong impressions or commands

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Naissance
    -0.61
    tagHelperRunner
    -0.56
    NgModule
    -0.56
    includegraphics
    -0.53
    plona
    -0.52
    RRect
    -0.50
     handi
    -0.49
     متعلقه
    -0.49
     ſtre
    -0.49
    JNIEnv
    -0.48
    POSITIVE LOGITS
     uttered
    1.25
     spoken
    1.05
     words
    1.03
     uttering
    0.99
     speech
    0.97
     utterances
    0.93
     talking
    0.85
     worded
    0.85
    peech
    0.85
    fromnode
    0.84
    Activations Density 0.586%

    No Known Activations