© 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. 20-GEMMASCOPE-RES-16K
    6. 11445
    Prev
    Next
    INDEX
    Explanations

    references to input fields and signals in a programming context

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

    code-related instances of the word "input" in programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forState
    -0.48
     thăng
    -0.47
    azole
    -0.47
     '<?
    -0.46
    ever
    -0.46
     strerror
    -0.45
    brengen
    -0.45
     dagen
    -0.44
     zoude
    -0.44
     weken
    -0.44
    POSITIVE LOGITS
     input
    1.23
     Input
    1.16
    input
    1.13
    Input
    1.13
     INPUT
    0.99
     getInput
    0.98
    INPUT
    0.97
    getInput
    0.97
     inputs
    0.92
     Inputs
    0.90
    Activations Density 0.069%

    No Known Activations