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. 14-GEMMASCOPE-RES-16K
    6. 4296
    Prev
    Next
    INDEX
    Explanations

    sections of the text that contain structured data or code-like formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CharStream
    -0.49
    знание
    -0.49
    šanās
    -0.45
    felde
    -0.44
    dieux
    -0.44
    ändern
    -0.44
     Nacionales
    -0.44
     tín
    -0.44
    RegistryLite
    -0.44
    țul
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.65
     CURIAM
    0.65
    ViewFeatures
    0.59
    featureID
    0.57
    writeField
    0.56
     Allegretto
    0.56
    Obrázky
    0.55
    IsContent
    0.55
    AutoScale
    0.54
    labelledby
    0.53
    Activations Density 0.069%

    No Known Activations