© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8125
    Prev
    Next
    INDEX
    Explanations

    JSON structure components and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.66
    engagent
    -0.59
    AccessorTable
    -0.56
     препратки
    -0.55
     betweenstory
    -0.54
    iodía
    -0.50
    exitRule
    -0.48
    تقاوى
    -0.48
    fitrión
    -0.47
    imageshack
    -0.47
    POSITIVE LOGITS
    ɵɵelementStart
    0.60
    TestingModule
    0.45
     snippetHide
    0.43
     jsPsych
    0.43
    ArgsConstructor
    0.40
    ioutil
    0.40
    strptime
    0.38
     initWithFrame
    0.37
     StatelessWidget
    0.36
    性和
    0.36
    Activations Density 0.499%

    No Known Activations