© 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. 28-GEMMASCOPE-RES-16K
    6. 8476
    Prev
    Next
    INDEX
    Explanations

    terms related to devices, systems, and materials used in technology and engineering contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical or mechanical components

    np_acts-logits-general · gemini-2.0-flash

    whose attributes or possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     потому
    -0.44
     bởi
    -0.42
    gól
    -0.39
    iertamente
    -0.36
    retanto
    -0.36
     porque
    -0.35
     مرئيه
    -0.35
     partout
    -0.35
     lắm
    -0.35
     Soporte
    -0.35
    POSITIVE LOGITS
     whose
    1.13
    whose
    0.98
     which
    0.86
     cuya
    0.76
     whofe
    0.75
     cuyo
    0.75
     Whose
    0.74
     cuyos
    0.73
     cuyas
    0.72
     capable
    0.71
    Activations Density 1.731%

    No Known Activations