© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13992
    Prev
    Next
    INDEX
    Explanations

    programming constructs and settings related to configurations and options

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

    Code, paths, or filenames

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    AndEndTag
    -0.93
    ftagPool
    -0.89
    OGND
    -0.87
    ScopeManager
    -0.84
    GOTREF
    -0.82
    httphttps
    -0.82
    AddTagHelper
    -0.82
     kasarigan
    -0.81
     nahilalakip
    -0.81
    <unused41>
    -0.81
    POSITIVE LOGITS
    MouseMove
    0.28
     mourir
    0.28
     migrantes
    0.28
     Atlántico
    0.26
     Rowland
    0.26
     aux
    0.26
     détour
    0.25
    RelativeLayout
    0.25
    AndGet
    0.24
    Égypte
    0.24
    Activations Density 1.290%

    No Known Activations