© 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. 0-GEMMASCOPE-RES-16K
    6. 7515
    Prev
    Next
    INDEX
    Explanations

    terms related to housing and the concept of separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.45
     Fresco
    -0.43
     мәкал
    -0.41
    Simple
    -0.41
    appé
    -0.41
    Auto
    -0.40
    gance
    -0.40
    mitteln
    -0.40
    Indented
    -0.40
    Agree
    -0.39
    POSITIVE LOGITS
    ambién
    0.63
     Course
    0.57
     course
    0.57
    enumi
    0.55
     COURSE
    0.54
    Portály
    0.52
    ItemBackground
    0.52
     dAtA
    0.51
    course
    0.50
     peman
    0.49
    Activations Density 0.345%

    No Known Activations