Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12903
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and statistical or mathematical terms related to analysis and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reportWebVitals
    -0.52
    getDoctrine
    -0.49
    LookAnd
    -0.44
     HasFactory
    -0.44
     ComVisible
    -0.43
    GOTREF
    -0.42
     OFDb
    -0.41
     المعيارى
    -0.40
    uxxxx
    -0.39
     AssemblyVersion
    -0.37
    POSITIVE LOGITS
     pinulongan
    0.54
    jspb
    0.51
    NUMX
    0.50
    Datuak
    0.47
    /**
    0.46
     Pingback
    0.46
     مشين
    0.45
    UIControlState
    0.43
     onBackPressed
    0.42
    ulso
    0.41
    Activations Density 1.633%

    No Known Activations