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. 10-GEMMASCOPE-RES-16K
    6. 11119
    Prev
    Next
    INDEX
    Explanations

    the presence of important terms or conditions related to eligibility and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     set
    -0.48
    -
    -0.47
     (
    -0.46
     re
    -0.43
     “
    -0.42
     no
    -0.42
     sy
    -0.42
     
    -0.41
     pos
    -0.40
    at
    -0.39
    POSITIVE LOGITS
    EDEFAULT
    0.93
     estekak
    0.92
    makeConstraints
    0.91
     חיצוניים
    0.86
    Décès
    0.86
     nakalista
    0.85
    sizeCache
    0.84
    WithIOException
    0.84
    rungsseite
    0.80
    enschappelijke
    0.80
    Activations Density 0.005%

    No Known Activations