© 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. 36-GEMMASCOPE-RES-16K
    6. 11809
    Prev
    Next
    INDEX
    Explanations

    references to "crystal" and related terms in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ordo
    -0.45
     Nod
    -0.44
    inherits
    -0.44
     creative
    -0.44
    berman
    -0.44
    ური
    -0.42
    Nod
    -0.42
    Touched
    -0.40
     Tong
    -0.40
     Felt
    -0.40
    POSITIVE LOGITS
     Signalez
    0.58
     BioLib
    0.57
    thâu
    0.52
    twimg
    0.50
     Comprometido
    0.49
     препратки
    0.47
     cardiaque
    0.46
    #+#
    0.46
    AnimationsModule
    0.46
    inheritDoc
    0.45
    Activations Density 0.291%

    No Known Activations