© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4187
    Prev
    Next
    INDEX
    Explanations

    references to the city of San Francisco

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

    Followed by location names

    np_acts-logits-general · gemini-2.0-flash

    San Francisco, Jose, Juan, Diego

    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
    ViewFeatures
    -0.64
     Verfahrens
    -0.60
     jLabel
    -0.58
     <<<<<<<<<<<<<<
    -0.58
    nologue
    -0.54
    Посилання
    -0.54
    UserScript
    -0.52
    InitVars
    -0.52
     lenker
    -0.52
     nakalista
    -0.51
    POSITIVE LOGITS
     Francisco
    0.60
    ctum
    0.52
     Diego
    0.52
     Franciscan
    0.50
    serif
    0.49
    Disk
    0.48
    born
    0.48
    zzleHttp
    0.47
    BORN
    0.47
    ibel
    0.46
    Activations Density 0.087%

    No Known Activations