© 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. 9950
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to layout and dimensions in a graphical context

    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
    Personendaten
    -0.67
     snippetHide
    -0.66
     незавершена
    -0.65
    OGND
    -0.63
    ParallelGroup
    -0.62
     ſelbſt
    -0.60
     deſſen
    -0.59
     Geſch
    -0.58
     FontWeight
    -0.57
     Geiſt
    -0.57
    POSITIVE LOGITS
     together
    0.43
    Together
    0.40
    together
    0.38
     Together
    0.36
     között
    0.36
    Personensuche
    0.36
     respectively
    0.35
     dø
    0.32
    在一起
    0.31
     вместе
    0.31
    Activations Density 0.995%

    No Known Activations