© 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. 37-GEMMASCOPE-RES-16K
    6. 4342
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to rights and entitlements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.65
     autorytatywna
    -0.55
    httphttps
    -0.54
    sarung
    -0.53
    +#+#
    -0.53
    balleur
    -0.53
     SEDS
    -0.53
    ########.
    -0.52
    pulseira
    -0.52
    BufferException
    -0.51
    POSITIVE LOGITS
     keyPressed
    0.34
    -\\
    0.34
     setMessage
    0.33
     particulars
    0.32
     censiti
    0.30
     chemin
    0.28
     -*-
    0.28
     Cog
    0.28
     divers
    0.28
    ):=\
    0.28
    Activations Density 0.430%

    No Known Activations