© 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. 24-GEMMASCOPE-RES-16K
    11. 13760
    Prev
    Next
    INDEX
    Explanations

    references to decision-making and the consequences of choices

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

    Preceding words of "make," "makes," "made," or "making"

    np_acts-logits-general · gemini-2.0-flash

    forms of "make"

    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
    oredCriteria
    -0.80
     Roskov
    -0.80
    Vidite
    -0.78
    NameInMap
    -0.71
    RegistryLite
    -0.70
    webElementXpaths
    -0.70
    TagMode
    -0.69
    IsMutable
    -0.67
    homonymie
    -0.65
     CreateTagHelper
    -0.65
    POSITIVE LOGITS
     make
    3.40
    make
    3.21
     makes
    3.13
     making
    3.13
    Make
    3.06
     Make
    3.05
     Making
    2.81
     MAKE
    2.79
    makes
    2.79
    Making
    2.78
    Activations Density 0.823%

    No Known Activations