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. 17-GEMMASCOPE-RES-16K
    6. 9041
    Prev
    Next
    INDEX
    Explanations

    specific historical and geographical terms and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lgari
    -0.83
    tableFuture
    -0.65
    tojas
    -0.61
    cokinetics
    -0.61
    HasForeignKey
    -0.59
    ConstraintMaker
    -0.58
    AddHtmlAttribute
    -0.58
    IGraphics
    -0.58
    IsMutable
    -0.56
    BagLayout
    -0.56
    POSITIVE LOGITS
     Vikipedi
    0.58
     era
    0.55
    campal
    0.52
    spheric
    0.51
    =[]
    
    0.51
    ]=>
    0.50
     socie
    0.49
     Church
    0.48
    BrowserModule
    0.48
     Glad
    0.47
    Activations Density 0.786%

    No Known Activations