Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 108462
    Prev
    Next
    INDEX
    Explanations

    terms related to punishment and punitive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    punishment and penalties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.48
    +#+
    -0.45
     hijas
    -0.38
     simplifié
    -0.38
     building
    -0.38
    viewWillAppear
    -0.38
     Gelegenheit
    -0.38
    Ever
    -0.38
     fatos
    -0.38
     rencont
    -0.37
    POSITIVE LOGITS
     punishment
    1.29
     Punishment
    1.23
     punish
    1.23
     penalty
    1.11
     penalties
    1.09
     punishments
    1.08
     Penalty
    1.07
     punished
    1.06
    Penalty
    1.05
     Penalties
    1.04
    Activations Density 0.041%

    No Known Activations