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. 7582
    Prev
    Next
    INDEX
    Explanations

    notations and names associated with artists, songs, and musical concepts

    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
    Personendaten
    -0.47
     unie
    -0.41
     Regierung
    -0.41
    ASED
    -0.41
    [@"
    -0.40
     tere
    -0.39
     év
    -0.39
    flexDirection
    -0.39
    "]
    -0.39
     chè
    -0.39
    POSITIVE LOGITS
     Мексичка
    0.80
    Przypisy
    0.77
    bewerken
    0.76
    StructEnd
    0.75
    </thead>
    0.75
    expandindo
    0.74
     المعيارى
    0.73
    ^(@)
    0.73
    出版年
    0.71
    neſs
    0.68
    Activations Density 1.699%

    No Known Activations