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
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 12356
    Prev
    Next
    INDEX
    Explanations

    phrases related to negligence and responsibility in medical or workplace contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gameserver
    -0.36
    Clik
    -0.35
     gynhyrchwyd
    -0.33
    Nationalité
    -0.32
    dubbo
    -0.32
     esqu
    -0.31
    Synchronization
    -0.31
     inspiration
    -0.29
    事业
    -0.28
     oppos
    -0.28
    POSITIVE LOGITS
     procedures
    1.37
     Procedures
    1.30
    procedures
    1.24
    Procedures
    1.16
     procedure
    1.11
     PROCEDURES
    1.06
     procédures
    1.05
     prosedur
    1.03
     procedimientos
    1.03
     Procedure
    1.02
    Activations Density 0.444%

    No Known Activations