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. 30-GEMMASCOPE-RES-16K
    6. 10916
    Prev
    Next
    INDEX
    Explanations

    numerical and coded data patterns in the text

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

    Followed by a number

    np_acts-logits-general · gemini-2.0-flash

    identifier followed by 4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.56
    Välislingid
    -0.51
    RenderAtEndOf
    -0.49
    存于互联网档案馆
    -0.42
     OMITBAD
    -0.42
     "");
    
    -0.40
    Tembelea
    -0.38
    Derbyniad
    -0.38
    __":
    
    -0.37
     Савезне
    -0.37
    POSITIVE LOGITS
    BeginContext
    0.47
    wapV
    0.41
     mål
    0.40
    tonode
    0.40
    Discriminator
    0.39
     BoxDecoration
    0.38
     lucru
    0.38
    resizingMask
    0.38
    хь
    0.37
     Pristupljeno
    0.37
    Activations Density 0.146%

    No Known Activations