Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 11940
    Prev
    Next
    INDEX
    Explanations

    references to geographic regions specifically focused on the southern areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.81
    d
    -0.70
    k
    -0.68
    Frame
    -0.66
    וק
    -0.65
    ള
    -0.64
     Blick
    -0.63
    蒙
    -0.62
     Fara
    -0.61
    リヤ
    -0.61
    POSITIVE LOGITS
    abestanden
    0.98
     createSlice
    0.97
     McKnight
    0.93
     Southern
    0.91
    styleType
    0.90
    Southern
    0.89
    Sucesor
    0.89
    ázaro
    0.88
    ⇑
    0.88
     AppDelegate
    0.88
    Activations Density 0.045%

    No Known Activations