© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 621
    Prev
    Next
    INDEX
    Explanations

    concepts related to unity and interconnectedness within various contexts

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

    following "to" or "several"

    np_acts-logits-general · gemini-2.0-flash

    to any, several more

    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
     للاسماء
    -0.48
    tagHelperRunner
    -0.47
     الرياضيه
    -0.42
     ISNI
    -0.40
    mbggenerated
    -0.39
    COLN
    -0.38
    NUMX
    -0.33
     isolado
    -0.33
     preventiva
    -0.33
    principalTable
    -0.32
    POSITIVE LOGITS
    aarrggbb
    0.56
    хьтан
    0.54
     skis
    0.51
    oa̍t
    0.46
    Chakra
    0.46
     transfieras
    0.46
     Administrativna
    0.45
     figur
    0.44
     Moro
    0.44
     camer
    0.43
    Activations Density 0.507%

    No Known Activations