© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 12947
    Prev
    Next
    INDEX
    Explanations

    specific instructions or guidelines related to gameplay mechanics in a game

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DIPSETTING
    -0.57
    principalColumn
    -0.51
    reggio
    -0.45
     viewDid
    -0.43
    ActionCreators
    -0.42
    buttonShape
    -0.41
    SceneManagement
    -0.40
    avigation
    -0.40
    currentThread
    -0.40
    ьаж
    -0.39
    POSITIVE LOGITS
     crafting
    0.66
     item
    0.66
     rare
    0.59
     rarer
    0.58
     rarity
    0.58
     items
    0.57
     crafted
    0.57
     recipe
    0.54
     ingredient
    0.53
     blueprints
    0.53
    Activations Density 0.166%

    No Known Activations