© 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. 2148
    Prev
    Next
    INDEX
    Explanations

    the verb "is" in various contexts, signaling assertions or states of being

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

    "is" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    It is + descriptor

    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
    География
    -0.54
    dorff
    -0.54
    itemBuilder
    -0.54
    楽しみにして
    -0.50
     Bescheid
    -0.49
    ्य
    -0.48
    which
    -0.48
    rifuge
    -0.47
    TableId
    -0.45
    trun
    -0.45
    POSITIVE LOGITS
     possible
    1.43
    possible
    1.24
     impossible
    1.17
     raining
    1.07
     POSSIBLE
    1.06
    Possible
    1.04
     snowing
    1.03
     poffible
    1.02
     advisable
    1.00
     posible
    0.99
    Activations Density 0.332%

    No Known Activations