Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4511
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to nanoparticles, particularly their properties and analyses

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

    XRD patterns and similar measurements

    np_acts-logits-general · gemini-2.0-flash

    europium, films, XRD, XPS

    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
    ########.
    -0.78
    writeFieldEnd
    -0.57
    fillType
    -0.56
     commandement
    -0.54
    OGND
    -0.54
    NameInMap
    -0.53
     saites
    -0.53
    randrange
    -0.53
    تقاوى
    -0.52
     vulné
    -0.52
    POSITIVE LOGITS
     XRD
    0.67
     XPS
    0.66
     samples
    0.65
     annealed
    0.62
     djur
    0.61
     pristine
    0.60
    Scheme
    0.59
     films
    0.59
     FTIR
    0.58
     sample
    0.58
    Activations Density 2.053%

    No Known Activations