Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8012
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their relationships in the context of entertainment or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     InputDecoration
    -0.57
    tagHelperRunner
    -0.57
    下载附件
    -0.53
    IUrlHelper
    -0.53
    basicConfig
    -0.52
    IsContent
    -0.52
    OrNil
    -0.51
    BASELINE
    -0.50
    ьаж
    -0.48
    npmjs
    -0.47
    POSITIVE LOGITS
    KindOfClass
    0.39
     deſt
    0.35
    OGND
    0.35
    tură
    0.34
     pleaſure
    0.33
     ups
    0.33
    ("/:
    0.32
     XNUMX
    0.32
    ++]
    0.31
     Tiefen
    0.31
    Activations Density 0.505%

    No Known Activations