© 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. 23-GEMMASCOPE-RES-16K
    11. 6076
    Prev
    Next
    INDEX
    Explanations

    numerical patterns or significance, particularly focusing on values related to cases and judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Према
    -0.73
    hdashline
    -0.71
    __((
    -0.70
    rawDesc
    -0.66
    下载附件
    -0.66
    malink
    -0.66
     تضيفلها
    -0.65
    WillAppear
    -0.63
    CppMethod
    -0.61
    rítica
    -0.60
    POSITIVE LOGITS
    PreferredItem
    0.59
     Malabar
    0.46
    9
    0.45
    0
    0.44
    4
    0.44
    8
    0.44
     nocturna
    0.44
    7
    0.43
     Weyl
    0.43
     conosco
    0.43
    Activations Density 1.652%

    No Known Activations