© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 774
    Prev
    Next
    INDEX
    Explanations

    conditional statements or hypothetical scenarios

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

    Preceding "return," "provide," "go," etc., after "would"

    np_acts-logits-general · gemini-2.0-flash

    would followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    Eure
    -0.42
    ("."
    -0.40
    "",
    -0.37
    (=)
    -0.36
     [*]
    -0.35
    [-]
    -0.34
    ('.')
    -0.34
     isSet
    -0.33
    (">>
    -0.32
     Jail
    -0.31
    POSITIVE LOGITS
    would
    0.90
     WOULD
    0.88
     would
    0.88
    Would
    0.87
     Would
    0.85
    JvmStatic
    0.72
    出版年
    0.67
     Gould
    0.66
    OGND
    0.65
    ########.
    0.61
    Activations Density 0.189%

    No Known Activations