© 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. 2-GEMMASCOPE-RES-16K
    11. 7059
    Prev
    Next
    INDEX
    Explanations

    expressions that indicate food quality, particularly highlighting food as delicious or tasty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.57
     '{@
    -0.51
    colhead
    -0.46
     محفوظة
    -0.45
    oa̍t
    -0.44
     Roskov
    -0.42
     linkovi
    -0.42
    ktop
    -0.41
     owing
    -0.41
    ArrowToggle
    -0.41
    POSITIVE LOGITS
     delicious
    1.47
     Delicious
    1.27
    delicious
    1.24
    Delicious
    1.20
     tasty
    1.13
     yummy
    1.04
     deliciosos
    0.92
     délicieux
    0.91
     delectable
    0.88
     deliciously
    0.88
    Activations Density 0.105%

    No Known Activations