© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9344
    Prev
    Next
    INDEX
    Explanations

    organizations and events related to community service and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.74
    OGND
    -0.67
    SourceChecksum
    -0.63
     चीज़ों
    -0.55
     surla
    -0.55
    itology
    -0.53
     caseros
    -0.52
    \{\\
    -0.52
     パンチラ
    -0.50
    ortium
    -0.50
    POSITIVE LOGITS
     chapter
    0.43
     member
    0.41
     Club
    0.41
     club
    0.40
     chapters
    0.39
     Clubs
    0.38
     Chapter
    0.38
     members
    0.38
     Activity
    0.37
     clubs
    0.37
    Activations Density 0.121%

    No Known Activations