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. 11-GEMMASCOPE-RES-16K
    6. 13278
    Prev
    Next
    INDEX
    Explanations

    mentions of public reactions and discussions regarding celebrities or events on social media platforms

    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
     kasarigan
    -0.62
    หวัด
    -0.53
    AndEndTag
    -0.51
    ContentAsync
    -0.51
    ChildScrollView
    -0.48
     році
    -0.46
    transQ
    -0.45
    KURZBESCHREIBUNG
    -0.44
     لیتر
    -0.44
    <bos>
    -0.44
    POSITIVE LOGITS
    ApiModelProperty
    0.78
    schild
    0.58
     meanwhile
    0.57
    IBarButtonItem
    0.56
     sarcas
    0.56
     reacted
    0.54
    enderror
    0.53
     Balk
    0.53
     Animate
    0.53
    OrNull
    0.52
    Activations Density 0.074%

    No Known Activations