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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7334
    Prev
    Next
    INDEX
    Explanations

    formatted elements of a user interface in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.60
    TemporalType
    -0.59
     оригіналу
    -0.59
     Wikimedijinoj
    -0.58
     useAppContext
    -0.57
    
    -0.54
     MonoBehaviour
    -0.50
    évaluateur
    -0.50
     BoxFit
    -0.50
    ʖ
    -0.50
    POSITIVE LOGITS
    )(((
    0.41
    umenical
    0.40
    agré
    0.40
    accro
    0.40
     delu
    0.38
    drained
    0.38
    dra
    0.38
    wapV
    0.37
     pragmatic
    0.37
    mannian
    0.36
    Activations Density 0.226%

    No Known Activations