© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13374
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal obligations or evidence of negligence

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

    followed by "any" or "anything"

    np_acts-logits-general · gemini-2.0-flash

    any or anything following certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CoreData
    -0.60
    ethene
    -0.54
    ChatColor
    -0.52
    PreAuthorize
    -0.51
    typeof
    -0.49
    ばかり
    -0.49
     defaultstate
    -0.48
     jeweils
    -0.48
    zsche
    -0.48
    ientôt
    -0.47
    POSITIVE LOGITS
     any
    4.26
    any
    3.35
    Any
    3.35
     Any
    3.24
     anything
    3.21
     ANY
    3.07
     anyone
    2.90
    任何
    2.87
    anything
    2.83
    ANY
    2.82
    Activations Density 2.142%

    No Known Activations