© 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. 18-GEMMASCOPE-RES-16K
    11. 474
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and significant places

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

    location or placement

    np_acts-logits-general · gemini-2.0-flash

    location and spatial relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >{@
    -0.71
    Hozzáférés
    -0.58
    Билгалдахарш
    -0.56
    >")
    -0.55
    missive
    -0.53
    ]")]
    -0.52
    latego
    -0.51
     ervan
    -0.51
    "]="
    -0.51
     /\.
    -0.50
    POSITIVE LOGITS
     in
    0.98
     inside
    0.81
     anywhere
    0.78
     within
    0.77
     somewhere
    0.76
     across
    0.70
     throughout
    0.70
     Paglinawan
    0.69
     elsewhere
    0.69
     at
    0.65
    Activations Density 0.927%

    No Known Activations