© 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. 25-GEMMASCOPE-RES-16K
    6. 6795
    Prev
    Next
    INDEX
    Explanations

    Arabic words and phrases related to location and specificity

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

    Arabic phrases or words related to preferences and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meu
    -0.54
     appart
    -0.52
     Administrativna
    -0.48
     Fros
    -0.48
    
    -0.47
     Signor
    -0.47
     Golfo
    -0.47
     Quell
    -0.47
     Minha
    -0.47
     Și
    -0.46
    POSITIVE LOGITS
    AnchorStyles
    0.73
     AppModule
    0.64
     المعرف
    0.62
    haustible
    0.62
    arschijnlijk
    0.59
     MessageBoxIcon
    0.59
    ución
    0.59
     imageNamed
    0.58
    iedenen
    0.57
    qiao
    0.57
    Activations Density 0.003%

    No Known Activations