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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53696
    Prev
    Next
    INDEX
    Explanations

    references to elasticity and elastic materials

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

    elastic strain, force, scattering, properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.93
    WindowConstants
    -0.85
    GEBURTSDATUM
    -0.84
     visualiser
    -0.80
    atouille
    -0.80
    стрее
    -0.77
     resourceCulture
    -0.77
    (!__
    -0.75
    SourceChecksum
    -0.74
    LookAnd
    -0.74
    POSITIVE LOGITS
    Elastic
    1.12
     Elastic
    1.03
    elastic
    1.03
     elastic
    0.95
     Elasticsearch
    0.91
     elas
    0.90
     Elas
    0.87
    elasticsearch
    0.74
     Elis
    0.73
     haram
    0.70
    Activations Density 0.022%

    No Known Activations