Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 7614
    Prev
    Next
    INDEX
    Explanations

    references to geological formations and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (!__
    -0.60
    bootstrapcdn
    -0.54
    Дере
    -0.54
    moke
    -0.51
    vency
    -0.51
    interopRequire
    -0.50
    เร็
    -0.47
    orexia
    -0.46
     kept
    -0.46
    mox
    -0.46
    POSITIVE LOGITS
     formations
    0.93
     Formations
    0.90
     rocks
    0.88
     outcrops
    0.85
     outcrop
    0.82
     Formation
    0.81
     exposures
    0.78
     formation
    0.78
    rocks
    0.75
     rock
    0.75
    Activations Density 0.217%

    No Known Activations