© 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. 10855
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to contracts and permissions

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

    Followed by "any"

    np_acts-logits-general · gemini-2.0-flash

    any, anything, anytime

    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
     للمعارف
    -0.56
    IBOutlet
    -0.51
    ChatColor
    -0.47
    schedulers
    -0.45
    ethene
    -0.45
     setObject
    -0.45
    /$',
    -0.44
    )))));
    -0.44
    才能
    -0.44
    ]=>
    -0.44
    POSITIVE LOGITS
     any
    4.12
    Any
    3.41
    any
    3.39
     Any
    3.29
     ANY
    3.17
     anything
    3.09
     qualquer
    2.98
    ANY
    2.96
     anyone
    2.95
     cualquier
    2.94
    Activations Density 1.374%

    No Known Activations