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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8520
    Prev
    Next
    INDEX
    Explanations

    elements and syntax related to programming code

    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
    MessageTagHelper
    -0.65
     nakalista
    -0.57
    bitField
    -0.56
    WriteBarrier
    -0.54
    ьаж
    -0.54
    MessageOf
    -0.54
    webElementXpaths
    -0.52
     Wicidata
    -0.52
     SwitchCompat
    -0.51
    ⅘
    -0.50
    POSITIVE LOGITS
    specifier
    0.66
    TokenName
    0.65
    TokenNameRBRACE
    0.61
    TokenNameLPAREN
    0.60
    TokenNameDOT
    0.57
    bibnamefont
    0.55
    bibfnamefont
    0.54
    bibinfo
    0.50
    TokenNameLBRACE
    0.50
    citenamefont
    0.48
    Activations Density 0.182%

    No Known Activations