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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15834
    Prev
    Next
    INDEX
    Explanations

    keywords related to web development and content management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related prefixes and suffixes

    np_acts-logits-general · gemini-2.0-flash

    .rb, .com, .d.ts, .html files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.69
     doInBackground
    -0.66
    SequentialGroup
    -0.63
    AutoScaleMode
    -0.61
    OfClass
    -0.56
     numberOfRows
    -0.55
    DECREF
    -0.55
    SaveChanges
    -0.54
     javafx
    -0.54
     charité
    -0.53
    POSITIVE LOGITS
     Next
    0.67
    gatsby
    0.63
    next
    0.62
    Next
    0.62
     Sanity
    0.58
     next
    0.58
     Gatsby
    0.57
    sanity
    0.56
    atsby
    0.56
     Tail
    0.55
    Activations Density 0.144%

    No Known Activations