© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4596
    Prev
    Next
    INDEX
    Explanations

    file-related operations and references in programming or scripting contexts

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

    Code snippets relating to files or decoding

    np_acts-logits-general · gemini-2.0-flash

    identifying files or locations

    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
    stateMutability
    -0.51
    styleType
    -0.50
     uLocal
    -0.49
    RTDA
    -0.49
     كومونز
    -0.48
     kasarigan
    -0.46
    MemoryWarning
    -0.45
    XmlAccessType
    -0.45
    UrlResolution
    -0.44
    MockMvc
    -0.43
    POSITIVE LOGITS
    ItemLayout
    0.44
     locating
    0.44
     identification
    0.42
    rungsseite
    0.41
     identifying
    0.41
    Locate
    0.40
     location
    0.40
    Personendaten
    0.39
     Secret
    0.39
    Décès
    0.37
    Activations Density 0.938%

    No Known Activations