© 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. 24-GEMMASCOPE-RES-16K
    6. 15827
    Prev
    Next
    INDEX
    Explanations

    the term "near" or phrases indicating proximity and distance

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

    "near"

    np_acts-logits-general · gemini-2.0-flash

    near followed by a descriptor

    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
    TAWA
    -0.65
     moindre
    -0.62
     riêng
    -0.59
    paragraphs
    -0.53
     Mundi
    -0.53
     BioLib
    -0.52
     autrement
    -0.52
    vábbi
    -0.50
     vidare
    -0.49
    عات
    -0.49
    POSITIVE LOGITS
    sighted
    0.92
     enough
    0.87
    enough
    0.77
     resourceCulture
    0.76
     misses
    0.74
    ness
    0.72
     completion
    0.71
     Enough
    0.65
    ish
    0.64
     estimés
    0.61
    Activations Density 0.099%

    No Known Activations