© 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. 28-GEMMASCOPE-RES-16K
    6. 4958
    Prev
    Next
    INDEX
    Explanations

    specific terms related to classifications and descriptors in both professional and creative contexts

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

    after "not," "non," or "un"

    np_acts-logits-general · gemini-2.0-flash

    heuristic has, secret key, unknown function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     letz
    -0.40
     groß
    -0.36
    wege
    -0.36
    vinger
    -0.35
    UKAN
    -0.34
    ávat
    -0.34
    EMBER
    -0.34
    FromArgb
    -0.34
     upor
    -0.34
    MIN
    -0.34
    POSITIVE LOGITS
     queſta
    0.61
     '',
    
    0.56
    RUnlock
    0.54
    ĵo
    0.52
    utnik
    0.52
    transQ
    0.50
     [],
    
    0.50
    hObject
    0.49
    __":
    
    0.49
    BindingResult
    0.48
    Activations Density 0.866%

    No Known Activations