© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7755
    Prev
    Next
    INDEX
    Explanations

    scientific terms and classifications related to chemistry and biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marcello
    -0.39
    ModelSerializer
    -0.39
    SourceChecksum
    -0.38
     CCL
    -0.37
     Ripley
    -0.37
    datastore
    -0.37
     PCD
    -0.37
     Englewood
    -0.36
    INGHAM
    -0.36
    akhstan
    -0.36
    POSITIVE LOGITS
    ETIC
    1.10
    istic
    1.05
    ONIC
    1.05
    matic
    1.01
    anic
    1.01
    olic
    1.00
    itic
    0.99
    atic
    0.98
    monic
    0.98
     Frederic
    0.98
    Activations Density 0.657%

    No Known Activations