© 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. 25-GEMMASCOPE-RES-16K
    6. 2325
    Prev
    Next
    INDEX
    Explanations

    references to methodologies and advanced techniques in research or technology

    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
    AddTagHelper
    -0.62
    djangoproject
    -0.62
    CppCodeGen
    -0.59
    ThroughAttribute
    -0.55
    cinogenicity
    -0.55
    Autoritní
    -0.54
    kespeare
    -0.53
    มาะ
    -0.53
     Aufgabe
    -0.52
     саны
    -0.51
    POSITIVE LOGITS
     methods
    2.14
     techniques
    1.87
     approaches
    1.73
    methods
    1.65
     methodologies
    1.57
     Methods
    1.56
     strategies
    1.55
     ways
    1.53
    techniques
    1.41
     méthodes
    1.40
    Activations Density 1.160%

    No Known Activations