© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3367
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses within the text

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

    URLs and web links in documents.

    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
    ArrowToggle
    -0.44
     ComVisible
    -0.42
    enschaften
    -0.41
     either
    -0.39
    تب
    -0.39
     exc
    -0.38
    ftagPool
    -0.38
     HttpNotFound
    -0.37
     fail
    -0.37
     про
    -0.37
    POSITIVE LOGITS
    www
    1.07
     www
    0.91
    youtu
    0.75
    ://
    0.64
    Www
    0.59
    github
    0.56
    WWW
    0.49
     Pemain
    0.49
    twitter
    0.48
     snippetHide
    0.47
    Activations Density 0.140%

    No Known Activations