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-2-9B
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 56
    Prev
    Next
    INDEX
    Explanations

    instances of the word "post" and its variations, indicating discussions or mentions of online content sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Notae
    -0.73
    DockStyle
    -0.67
    Aholisi
    -0.66
    ExtendWith
    -0.66
    ArrowToggle
    -0.65
    DebuggerNonUser
    -0.65
     Italijanski
    -0.63
    ListItemIcon
    -0.62
    TargetException
    -0.59
    MeasureSpec
    -0.58
    POSITIVE LOGITS
     posted
    0.76
     posting
    0.71
     Posting
    0.65
    posted
    0.59
     posts
    0.57
    Posting
    0.57
     postings
    0.56
    post
    0.55
    posting
    0.55
     post
    0.54
    Activations Density 0.012%

    No Known Activations