© 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. 16-GEMMASCOPE-RES-16K
    11. 4786
    Prev
    Next
    INDEX
    Explanations

    complex processes involving systematic steps and iterations

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

    Repeating a process

    np_acts-logits-general · gemini-2.0-flash

    repeating actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.56
    انگلیسی
    -0.55
    فية
    -0.53
    onomia
    -0.52
    íncia
    -0.52
    mobileqq
    -0.52
    opsida
    -0.51
    onomic
    -0.51
     candidacy
    -0.50
    hoeddwyd
    -0.49
    POSITIVE LOGITS
     Repeat
    1.85
     repeat
    1.83
    Repeat
    1.74
    repeat
    1.55
     repeating
    1.46
     repeats
    1.38
     Repe
    1.35
    REPEAT
    1.30
     repeated
    1.29
    repe
    1.25
    Activations Density 0.551%

    No Known Activations