© 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. 5122
    Prev
    Next
    INDEX
    Explanations

    terms related to parenting and family resources

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

    "Impact Factory" email addresses

    np_acts-logits-general · gemini-2.0-flash

    factory, burpees, chic

    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
    posedge
    -0.64
     AssemblyTitle
    -0.56
    Gön
    -0.54
    UserScript
    -0.53
    tě
    -0.51
    essandro
    -0.51
    etCode
    -0.50
     Ababa
    -0.49
    vstack
    -0.49
     Moines
    -0.49
    POSITIVE LOGITS
    ofthe
    0.79
    inthe
    0.65
    ands
    0.63
    onthe
    0.61
    and
    0.60
    andte
    0.57
    of
    0.57
    tothe
    0.55
    ofman
    0.53
    anden
    0.52
    Activations Density 0.412%

    No Known Activations