© 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. 22-GEMMASCOPE-RES-16K
    11. 10882
    Prev
    Next
    INDEX
    Explanations

    concepts related to potential benefits and opportunities for organizations and individuals

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

    "exploit" or "full use"

    np_acts-logits-general · gemini-2.0-flash

    taking full advantage

    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
    ########.
    -0.71
     doInBackground
    -0.64
    oredCriteria
    -0.58
    الإنجليزية
    -0.55
     venons
    -0.53
     getchar
    -0.52
    ̈́
    -0.51
    ومة
    -0.50
    writeFieldEnd
    -0.50
     Scritto
    -0.49
    POSITIVE LOGITS
     exploit
    1.71
     exploiting
    1.70
     capitalize
    1.65
     aprovechar
    1.62
     sfr
    1.61
     aprovecha
    1.60
     exploited
    1.60
     exploitation
    1.56
     memanfaatkan
    1.55
     aprove
    1.55
    Activations Density 0.311%

    No Known Activations