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. 9088
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords associated with data storage and application management

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

    HTML or citation context

    np_acts-logits-general · gemini-2.0-flash

    Container outer wrapper

    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
     ujednoznacz
    -0.61
    Бахар
    -0.58
     CreateTagHelper
    -0.57
    PullParser
    -0.56
    MergeFrom
    -0.55
    rufen
    -0.53
    miede
    -0.53
    TagMode
    -0.53
     resourceCulture
    -0.51
    blurRadius
    -0.51
    POSITIVE LOGITS
     container
    0.80
    container
    0.78
     inner
    0.73
     outer
    0.72
     content
    0.70
    inner
    0.69
     Content
    0.68
    outer
    0.68
    content
    0.67
    wrapper
    0.67
    Activations Density 0.229%

    No Known Activations