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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 3213
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to particle physics and thermodynamics

    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
    devamını
    -0.66
    NSIndexPath
    -0.58
    hyrchwyd
    -0.57
    Geplaatst
    -0.54
    XmlAccessType
    -0.54
     ")");
    -0.54
     Mero
    -0.53
    BeginInit
    -0.53
    })`
    -0.51
     "/";
    -0.51
    POSITIVE LOGITS
     potential
    0.95
     potentials
    0.85
    potential
    0.83
    Potential
    0.83
     repulsive
    0.80
     attractive
    0.79
     Potential
    0.79
     POTENTIAL
    0.75
    attractive
    0.73
     Attractive
    0.73
    Activations Density 1.730%

    No Known Activations