© 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. 2-GEMMASCOPE-RES-16K
    6. 3371
    Prev
    Next
    INDEX
    Explanations

    terms indicating opposition or resistance to various actions or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zczegól
    -0.51
    面目
    -0.51
     SETTLE
    -0.51
     Yarm
    -0.50
     دریافت‌شده
    -0.50
     acu
    -0.50
    reszcie
    -0.50
     Rambo
    -0.49
    Palmar
    -0.48
     ég
    -0.48
    POSITIVE LOGITS
     inhibiting
    1.52
     suppress
    1.46
     inhibit
    1.42
     suppressing
    1.41
     suppresses
    1.39
     inhibits
    1.33
     prohibiting
    1.31
     inhibition
    1.30
     suppression
    1.29
     prohibit
    1.29
    Activations Density 0.232%

    No Known Activations