© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5072
    Prev
    Next
    INDEX
    Explanations

    terms related to processing and manipulation of data or objects

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

    Preceding "appropriate" or "proper"

    np_acts-logits-general · gemini-2.0-flash

    proper or desired state

    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
    stateProvider
    -0.65
    AndEndTag
    -0.58
    +#+#
    -0.57
    tagHelperRunner
    -0.57
    tonsoft
    -0.54
    StoryboardSegue
    -0.53
     发表于
    -0.53
    homonymie
    -0.52
    IVEREF
    -0.52
     ProtoMessage
    -0.52
    POSITIVE LOGITS
     appropriate
    3.08
    appropriate
    2.61
     Appropriate
    2.58
    Appropriate
    2.50
     proper
    2.46
     suitable
    2.41
     correct
    2.31
    proper
    2.15
     APPROPRI
    2.10
     juiste
    2.02
    Activations Density 1.046%

    No Known Activations