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. 25-GEMMASCOPE-RES-16K
    6. 12347
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "the" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimédia
    -0.56
    another
    -0.53
    tlv
    -0.52
    OGND
    -0.52
    own
    -0.51
     dasselbe
    -0.50
    ۜ
    -0.50
     another
    -0.50
    finally
    -0.50
     wezen
    -0.50
    POSITIVE LOGITS
     rest
    0.93
    saurus
    0.76
     remainder
    0.74
     following
    0.72
     slightest
    0.70
     entire
    0.69
     very
    0.67
     heck
    0.66
     latter
    0.66
    Билгалдахарш
    0.66
    Activations Density 0.286%

    No Known Activations