Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 6805
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stddef
    -0.55
    ErrorListener
    -0.52
    -
    -0.45
    cmath
    -0.45
     PyTuple
    -0.41
    aliana
    -0.41
     Part
    -0.40
    _
    -0.40
    ℕ
    -0.39
    semver
    -0.39
    POSITIVE LOGITS
     houſe
    1.10
     purpoſe
    1.08
     pleaſure
    1.01
     myſelf
    1.00
     greateſt
    1.00
     Theſe
    0.99
     Jefus
    0.98
     Diſ
    0.96
     ſame
    0.94
     theſe
    0.89
    Activations Density 0.135%

    No Known Activations