© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14320
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming functions and input-output operations

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

    input parameters and their values in function signatures and method calls.

    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
    MemoryWarning
    -0.36
    κτηρισ
    -0.35
    fromCharCode
    -0.32
    +#+#
    -0.32
     AssemblyProduct
    -0.31
    aulted
    -0.31
    urma
    -0.31
    AutoField
    -0.31
    AnimationsModule
    -0.29
    DrawerToggle
    -0.29
    POSITIVE LOGITS
     input
    2.05
     inputs
    1.77
     Input
    1.70
    input
    1.68
    Input
    1.59
     INPUT
    1.56
     Inputs
    1.53
    INPUT
    1.48
    输入
    1.44
     getInput
    1.41
    Activations Density 1.043%

    No Known Activations