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. 15-GEMMASCOPE-RES-16K
    6. 8577
    Prev
    Next
    INDEX
    Explanations

    sequences of formatted strings or preferences related to notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     im
    -0.59
     Im
    -0.53
    as
    -0.52
    Im
    -0.51
     cor
    -0.50
     The
    -0.49
    im
    -0.46
     a
    -0.45
    pe
    -0.45
     au
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    1.41
     myſelf
    1.06
     surla
    1.05
     JpaRepository
    1.01
     itſelf
    1.01
    ſelves
    0.97
    bootstrapcdn
    0.97
     }}$}
    0.96
     Normdatei
    0.95
    \{\\
    0.93
    Activations Density 0.016%

    No Known Activations