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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 6074
    Prev
    Next
    INDEX
    Explanations

    elements of Objective-C syntax and programming constructs related to error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.62
    ropolitana
    -0.57
     []:
    -0.57
    PickerController
    -0.55
    Xna
    -0.55
    asions
    -0.53
    مئ
    -0.52
    PullParser
    -0.52
    RunAsync
    -0.52
    setcounter
    -0.52
    POSITIVE LOGITS
    GEBURTSDATUM
    0.62
    :+:
    0.58
    évaluateur
    0.54
     Autorizaciones
    0.54
    Попис
    0.53
    ellees
    0.52
    DeleteBehavior
    0.52
    ثيق
    0.51
    JsonPropertyName
    0.49
    ૌ
    0.48
    Activations Density 0.311%

    No Known Activations