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. 16-GEMMASCOPE-RES-16K
    6. 5085
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation involving sets and operations

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

    Sequences enclosed in curly braces

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NgModule
    -0.94
     Audiodateien
    -0.91
    Хьажоргаш
    -0.89
     متعلقه
    -0.88
    __':
    
    -0.84
     surla
    -0.84
    MemoryWarning
    -0.79
    providedIn
    -0.76
     الرياضيه
    -0.76
    URLException
    -0.75
    POSITIVE LOGITS
     cauſe
    0.53
     صوتيه
    0.53
    hogy
    0.52
     blessing
    0.50
    lindungan
    0.50
    печат
    0.49
     Seleccione
    0.49
     Lippen
    0.48
    assium
    0.48
    KELEY
    0.47
    Activations Density 0.943%

    No Known Activations