© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4600
    Prev
    Next
    INDEX
    Explanations

    occurrences of numeric values and file paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.94
    rungsseite
    -0.90
    verwijspagina
    -0.89
    脚注の使い方
    -0.87
    ConstraintMaker
    -0.83
     AssemblyProduct
    -0.83
    homonymie
    -0.82
    StructEnd
    -0.81
    SourceChecksum
    -0.80
    Scénario
    -0.79
    POSITIVE LOGITS
    ".$_
    0.69
    ('.');
    0.58
    AILABLE
    0.54
    :%.
    0.54
    uiente
    0.53
    =$_
    0.51
    eſ
    0.50
    ('.'
    0.50
    mathrm
    0.49
    "]/
    0.49
    Activations Density 0.168%

    No Known Activations