© 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. 6844
    Prev
    Next
    INDEX
    Explanations

    various patterns and structures in formatted text

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

    Code-related syntax or special characters

    np_acts-logits-general · gemini-2.0-flash

    technical jargon and code snippets

    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
    enumi
    -0.56
     OMITBAD
    -0.46
     estekak
    -0.46
     <<<<<<<<<<<<<<
    -0.46
    expandindo
    -0.40
    󠁮
    -0.40
    enumii
    -0.40
    ]")]
    -0.39
    يكب
    -0.38
    endphp
    -0.37
    POSITIVE LOGITS
     extérieures
    0.49
     deose
    0.49
    XmlAccessType
    0.47
     quedado
    0.46
     CascadeType
    0.46
    marvin
    0.44
    extAlignment
    0.43
    îtra
    0.43
    ControllerAdvice
    0.43
     OBITUARY
    0.43
    Activations Density 1.072%

    No Known Activations