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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3939
    Prev
    Next
    INDEX
    Explanations

    numeric values and their representations in various contexts

    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
    8
    -1.41
     Eight
    -1.26
     Eighth
    -1.25
     eight
    -1.23
     eighth
    -1.16
     EIGHT
    -1.15
    8
    -1.08
    Eight
    -1.06
    八
    -1.03
     VIII
    -1.00
    POSITIVE LOGITS
    viewDidLoad
    0.49
    談社
    0.46
    glBindBuffer
    0.43
    ỡng
    0.42
    chluss
    0.41
     opge
    0.41
    ↻
    0.40
    𝟶
    0.39
    abetes
    0.39
     Komponist
    0.39
    Activations Density 0.694%

    No Known Activations