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. 21-GEMMASCOPE-RES-16K
    6. 14302
    Prev
    Next
    INDEX
    Explanations

    forms of the word "ver"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    :]:
    -0.59
    länger
    -0.55
    längerung
    -0.51
     Audiodateien
    -0.50
     Trouver
    -0.48
    Contribute
    -0.47
     propOrder
    -0.45
    Secondly
    -0.45
     المرجع
    -0.45
    anteed
    -0.44
    POSITIVE LOGITS
     Verm
    0.78
    bootstrapcdn
    0.66
    ThroughAttribute
    0.64
    Ver
    0.62
     verru
    0.62
     विश्वसनीयता
    0.61
     VER
    0.61
     StringVar
    0.60
     Verma
    0.59
     Ver
    0.58
    Activations Density 0.088%

    No Known Activations