© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3766
    Prev
    Next
    INDEX
    Explanations

    references to variables in mathematical expressions or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raiſ
    -0.84
    ✨:
    -0.80
    wiſe
    -0.80
    ===============
    -0.80
    ."</
    -0.79
     Alha
    -0.79
     ſeveral
    -0.78
     pleaſure
    -0.78
     doubtnut
    -0.77
     ་་
    -0.77
    POSITIVE LOGITS
     r
    2.24
    r
    2.13
    R
    1.50
     R
    1.41
    𝑟
    1.14
    getR
    1.08
    rr
    1.04
    rA
    1.00
     rRNA
    0.99
    rrr
    0.99
    Activations Density 0.205%

    No Known Activations