© 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. 38-GEMMASCOPE-RES-16K
    6. 9060
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated notations or qualifiers

    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
    VIAF
    -0.62
    IBarButtonItem
    -0.52
    hundreds
    -0.50
     hundreds
    -0.48
     centaines
    -0.47
     HUND
    -0.45
    Hundreds
    -0.45
     "..\..\..\
    -0.45
    astify
    -0.45
     Hundreds
    -0.44
    POSITIVE LOGITS
     fifteen
    0.61
     twelve
    0.60
     thirteen
    0.59
     fourteen
    0.58
    1
    0.53
     Fifteen
    0.52
     sixteen
    0.52
    Fifteen
    0.51
     eleven
    0.49
     ten
    0.49
    Activations Density 1.287%

    No Known Activations