© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14558
    Prev
    Next
    INDEX
    Explanations

    specific relationships and familial connections within a genealogy context

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

    Name followed by "was" or a comma

    np_acts-logits-general · gemini-2.0-flash

    names in lists

    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
    NameInMap
    -0.63
     AspNetCore
    -0.58
    thâu
    -0.58
    FormTagHelper
    -0.55
    ябре
    -0.51
    onOptions
    -0.49
    ourced
    -0.49
     Tangerang
    -0.47
    تیب
    -0.47
     Bailly
    -0.47
    POSITIVE LOGITS
     Johnny
    0.58
     Lillie
    0.57
     Johnnie
    0.55
    Johnny
    0.54
     abgerufen
    0.53
    openzeppelin
    0.52
     Willie
    0.51
     Jimmy
    0.51
     Danny
    0.50
    Jimmy
    0.49
    Activations Density 0.101%

    No Known Activations