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

    Neuronpedia

    APICircuit 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. 11-GEMMASCOPE-RES-16K
    6. 5489
    Prev
    Next
    INDEX
    Explanations

    instructions and specifications related to formatting or structuring elements in a document or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoSize
    -0.51
     дописавши
    -0.45
    ApiModelProperty
    -0.43
    Бахар
    -0.42
    thâu
    -0.41
    contentValues
    -0.41
     femmin
    -0.41
     LINCOLN
    -0.40
     Lincoln
    -0.40
     pasteles
    -0.39
    POSITIVE LOGITS
    يكب
    0.73
    Autoritní
    0.71
    >*/
    0.70
    NUMX
    0.70
     للاسماء
    0.70
     AttributeSet
    0.67
     Biôgrafia
    0.67
     ExecuteAsync
    0.67
    intios
    0.66
    bewerken
    0.65
    Activations Density 1.738%

    No Known Activations