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. 31-GEMMASCOPE-RES-16K
    6. 9294
    Prev
    Next
    INDEX
    Explanations

    query parameters in URLs or web requests

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

    question mark characters (?) that appear at the end of URLs and queries.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     objet
    -0.41
    RenderAtEndOf
    -0.37
     titu
    -0.36
     yourselves
    -0.36
     objects
    -0.34
     bles
    -0.33
    ội
    -0.32
     бър
    -0.32
     contacter
    -0.31
     theoretical
    -0.31
    POSITIVE LOGITS
    SequentialGroup
    0.59
    HostException
    0.56
    Personendaten
    0.53
     uintptr
    0.52
    ferrer
    0.52
    :+:
    0.49
    Hentet
    0.47
    getClassLoader
    0.46
     дописавши
    0.46
    SpringBootTest
    0.46
    Activations Density 0.168%

    No Known Activations