© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 9670
    Prev
    Next
    INDEX
    Explanations

    elements related to expectations and contrasts within narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.65
    存于互联网档案馆
    -0.64
    yntaxException
    -0.64
    OGND
    -0.63
    GraphicsUnit
    -0.60
     consultato
    -0.58
    adaptiveStyles
    -0.58
     onPostExecute
    -0.55
    ::$_
    -0.54
    ftagPool
    -0.53
    POSITIVE LOGITS
     actually
    1.58
     really
    1.57
     eigenlijk
    1.38
     eigentlich
    1.37
    actually
    1.35
    really
    1.33
     frankly
    1.30
     honestly
    1.30
     tbh
    1.29
     egentlig
    1.22
    Activations Density 0.494%

    No Known Activations