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. 10-GEMMASCOPE-RES-16K
    6. 15579
    Prev
    Next
    INDEX
    Explanations

    scientific processes related to sample preparation and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.68
     defaultstate
    -0.67
     [].
    -0.64
    providedIn
    -0.59
     Historically
    -0.56
    ulti
    -0.56
    PutMapping
    -0.55
     fieldNum
    -0.54
    */].
    -0.53
    feira
    -0.51
    POSITIVE LOGITS
     again
    0.80
    again
    0.80
    Again
    0.76
     AGAIN
    0.75
     Again
    0.73
     novamente
    0.64
     tartalomajánló
    0.63
    AGAIN
    0.62
     igjen
    0.59
    又被
    0.58
    Activations Density 0.421%

    No Known Activations