© 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. 21-GEMMASCOPE-RES-16K
    11. 2253
    Prev
    Next
    INDEX
    Explanations

    tokens or identifiers that likely represent numerical values or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     peito
    -0.49
    FontAwesomeIcon
    -0.44
     limone
    -0.42
     printemps
    -0.42
     Frühling
    -0.41
     Spring
    -0.40
     Frühjahr
    -0.40
    (&:
    -0.40
     MonoBehaviour
    -0.39
    Personendaten
    -0.39
    POSITIVE LOGITS
     seventh
    1.23
     Seventh
    1.11
    7
    1.09
     Seven
    1.00
    seventh
    0.99
     seven
    0.99
     SEVENTH
    0.98
    Seventh
    0.98
    ⑦
    0.97
     VII
    0.97
    Activations Density 0.254%

    No Known Activations