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. 20-GEMMASCOPE-RES-16K
    6. 5290
    Prev
    Next
    INDEX
    Explanations

    references to concepts of health and illness

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

    Code snippets/programming language

    np_acts-logits-general · gemini-2.0-flash

    return statement in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.67
    oneofs
    -0.61
     GetComponent
    -0.53
    styleUrls
    -0.52
    invokeLater
    -0.51
    >*/
    -0.49
    วย
    -0.49
    Portail
    -0.48
     harp
    -0.46
     NavController
    -0.45
    POSITIVE LOGITS
    featureID
    0.63
     saurait
    0.59
    يميديا
    0.57
    ++];
    0.56
     ProtoMessage
    0.54
     AssemblyProduct
    0.53
     namun
    0.52
    satunya
    0.51
    taxia
    0.51
     مشين
    0.51
    Activations Density 0.035%

    No Known Activations