© 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. 33-GEMMASCOPE-RES-16K
    11. 7491
    Prev
    Next
    INDEX
    Explanations

    intense emotional interactions related to conflict and desire

    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
    itself
    -0.60
     itself
    -0.60
    newtheorem
    -0.50
    AxisAlignment
    -0.48
     Itself
    -0.46
    StructEnd
    -0.45
    IBAction
    -0.41
     kendini
    -0.38
     sobie
    -0.38
    ativen
    -0.38
    POSITIVE LOGITS
    Cyfarwyddwr
    0.68
     ProtoMessage
    0.60
     gently
    0.51
     coerci
    0.51
    +#+#
    0.50
     tenderly
    0.50
     privately
    0.49
     lovingly
    0.46
     CallOverrides
    0.45
    InitVars
    0.43
    Activations Density 0.393%

    No Known Activations