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. 17-GEMMASCOPE-RES-16K
    6. 9173
    Prev
    Next
    INDEX
    Explanations

    structural elements and commands in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -0.91
    a
    -0.89
    +#+#
    -0.88
    o
    -0.82
    n
    -0.80
    E
    -0.80
    S
    -0.80
    P
    -0.80
    p
    -0.80
    h
    -0.79
    POSITIVE LOGITS
     myſelf
    1.35
     themſelves
    1.25
     Theſe
    1.19
     purpoſe
    1.17
     doubtnut
    1.15
     himſelf
    1.15
     Monfieur
    1.14
     ſeveral
    1.08
     pleaſure
    1.08
     whoſe
    1.07
    Activations Density 0.610%

    No Known Activations