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. 0-GEMMASCOPE-RES-16K
    6. 9340
    Prev
    Next
    INDEX
    Explanations

    references to tents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.68
    χρι
    -0.65
    BufferException
    -0.55
     désolés
    -0.53
     SqlDbType
    -0.52
     ErrInvalid
    -0.51
     industrias
    -0.50
    formis
    -0.49
     UNIVERSIT
    -0.49
     sepen
    -0.49
    POSITIVE LOGITS
    berry
    1.08
    BERRY
    0.92
    Berry
    0.85
     CreateTagHelper
    0.78
    berries
    0.76
    __':
    0.69
     tent
    0.67
     Berry
    0.66
    textbf
    0.65
     tents
    0.63
    Activations Density 0.149%

    No Known Activations