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. 18-GEMMASCOPE-RES-16K
    6. 10734
    Prev
    Next
    INDEX
    Explanations

    terms related to cameras and recording devices

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

    Scientific instruments and equipment

    np_acts-logits-general · gemini-2.0-flash

    cameras, meters, spectrometers, radios, clocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     محفوظة
    -0.69
     Himo
    -0.61
     >=",
    -0.54
     forgiven
    -0.54
     оригіналу
    -0.53
    holdet
    -0.52
    unhofer
    -0.52
    Portale
    -0.52
    stateMutability
    -0.51
    archical
    -0.50
    POSITIVE LOGITS
     installed
    0.80
     operating
    0.70
     operated
    0.70
     instalada
    0.69
     equipment
    0.67
    operating
    0.66
     apparatus
    0.65
     portatil
    0.65
     manufacturer
    0.65
     Installed
    0.64
    Activations Density 0.900%

    No Known Activations