© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 14282
    Prev
    Next
    INDEX
    Explanations

    terms related to machine learning error handling and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.60
    الحياه
    -0.49
    #+#
    -0.45
    XmlAccessType
    -0.40
    
    -0.39
    zewod
    -0.38
     RouterModule
    -0.38
    󠁣
    -0.37
     AssemblyTitle
    -0.37
    andExpect
    -0.37
    POSITIVE LOGITS
     batch
    0.69
     train
    0.68
     samples
    0.63
     dataset
    0.63
     batches
    0.60
     labels
    0.59
     Train
    0.59
    dataset
    0.58
     Dataset
    0.58
     label
    0.57
    Activations Density 0.368%

    No Known Activations