© 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. 12-GEMMASCOPE-RES-16K
    6. 5713
    Prev
    Next
    INDEX
    Explanations

    references to accessing drives and storage in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.35
     Mexicano
    -0.31
     luchando
    -0.30
     промежу
    -0.29
     corriendo
    -0.28
    FieldBuilder
    -0.28
     remplacé
    -0.28
     Flü
    -0.28
     nessuna
    -0.28
     journal
    -0.27
    POSITIVE LOGITS
     gynhyrchwyd
    0.71
     EconPapers
    0.66
     propOrder
    0.61
    нгред
    0.61
    存于互联网档案馆
    0.56
    GOTREF
    0.56
    clerview
    0.56
    DriverManager
    0.55
    AutoresizingMask
    0.55
     queſta
    0.55
    Activations Density 0.998%

    No Known Activations