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-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 936
    Prev
    Next
    INDEX
    Explanations

    specific locations and their geographical descriptions

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

    details related to locations and geographical features

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

    distance and location references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     multiple
    -0.55
    ษา
    -0.52
     الاطلاع
    -0.49
     plancher
    -0.48
    hemiah
    -0.47
     experts
    -0.45
    供
    -0.44
    theria
    -0.44
    handleSubmit
    -0.44
     due
    -0.44
    POSITIVE LOGITS
     vicinity
    0.73
     immédi
    0.73
     administrativos
    0.69
    towards
    0.68
     Jefus
    0.67
     femininas
    0.67
     civilisation
    0.65
     ſtate
    0.65
    Personendaten
    0.64
     aproximado
    0.64
    Activations Density 0.044%

    No Known Activations