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. 22-GEMMASCOPE-RES-16K
    6. 7951
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terminologies related to algebra and operators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical identities or operators

    np_acts-logits-general · gemini-2.0-flash

    identity, unit, diagonal, zero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.64
    Zitat
    -0.62
    \{\\
    -0.51
    .*")]
    -0.50
    AccessException
    -0.50
    نح
    -0.50
     Audiodateien
    -0.48
    drawSprites
    -0.47
     nemlig
    -0.47
     doInBackground
    -0.47
    POSITIVE LOGITS
     identity
    1.00
    identity
    0.89
     Identity
    0.86
    Identity
    0.79
     Id
    0.78
     id
    0.78
    id
    0.77
     unit
    0.74
     Unit
    0.72
    Id
    0.71
    Activations Density 1.676%

    No Known Activations