© 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. 23-GEMMASCOPE-RES-16K
    6. 9106
    Prev
    Next
    INDEX
    Explanations

    references to space and capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 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
     المعيارى
    -0.37
     nocturne
    -0.34
     bruja
    -0.33
     nocturn
    -0.33
     świ
    -0.33
     estiver
    -0.32
     custos
    -0.31
    /**
    -0.31
     påver
    -0.30
    #+#
    -0.30
    POSITIVE LOGITS
     space
    0.74
     ample
    0.66
     plenty
    0.66
     ruimte
    0.66
    Spaces
    0.65
     espacio
    0.65
    Plenty
    0.64
    plenty
    0.63
    Space
    0.62
    space
    0.62
    Activations Density 0.184%

    No Known Activations