© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 12383
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to metals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anya
    -0.93
     تضيفلها
    -0.93
    ]--;
    -0.89
     AssemblyCulture
    -0.86
     RDC
    -0.84
     ochre
    -0.84
     Partagez
    -0.84
     <",
    -0.82
     errorCode
    -0.81
     SAGE
    -0.81
    POSITIVE LOGITS
     metal
    1.13
    metal
    1.11
     Metal
    1.10
    METAL
    1.08
     METAL
    1.03
    Metal
    1.02
     meat
    0.98
     metals
    0.90
    metals
    0.88
     Meat
    0.88
    Activations Density 0.052%

    No Known Activations