© 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. 10080
    Prev
    Next
    INDEX
    Explanations

    elements related to requests or actions regarding returns and product replacements

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

    Code, mutations, or mathematical expressions nearby

    np_acts-logits-general · gemini-2.0-flash

    genetic mutation information

    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
     Перейти
    -0.74
     Saltar
    -0.63
    SEGUIR
    -0.56
     Архів
    -0.53
    ὖ
    -0.53
     NDEBUG
    -0.53
    ”、“
    -0.47
    ResumeLayout
    -0.46
    hoge
    -0.45
    яз
    -0.44
    POSITIVE LOGITS
     Roskov
    1.11
    ')))
    1.09
    IsMutable
    1.08
    })$}
    0.97
    LookAnd
    0.94
    InstrumentedTest
    0.90
    ]]]
    0.88
     protoimpl
    0.87
    ')],
    0.86
    }}}}
    0.86
    Activations Density 3.350%

    No Known Activations