© 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. 2476
    Prev
    Next
    INDEX
    Explanations

    phrases indicating distance or extent

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

    "far as"

    np_acts-logits-general · gemini-2.0-flash

    as far as

    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
    EndContext
    -0.82
    NameInMap
    -0.79
    randomUUID
    -0.72
     wireType
    -0.69
    MLLoader
    -0.68
    IVEREF
    -0.67
    NewGuid
    -0.66
     protoimpl
    -0.65
     contextLoads
    -0.65
     Italijanski
    -0.65
    POSITIVE LOGITS
    homonymie
    0.52
     inggris
    0.47
     they
    0.45
    locken
    0.43
     passés
    0.42
    æs
    0.41
     fibra
    0.41
     PSOE
    0.41
     suprême
    0.41
    ertale
    0.41
    Activations Density 0.081%

    No Known Activations