© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6579
    Prev
    Next
    INDEX
    Explanations

    references to the creation of processes or objects, often including attribution to authors and tools used

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PullParser
    -0.59
     bain
    -0.55
     RSP
    -0.55
    áról
    -0.54
    jooq
    -0.54
     CanadaChoose
    -0.54
    gamento
    -0.53
     ASK
    -0.52
    хь
    -0.51
    пара
    -0.51
    POSITIVE LOGITS
     Created
    1.36
    Created
    1.23
     PhpStorm
    1.06
     AssemblyTitle
    0.94
    created
    0.93
     created
    0.93
     CREATED
    0.81
     محفوظة
    0.77
    CREATED
    0.69
     للاسماء
    0.67
    Activations Density 0.015%

    No Known Activations