© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12874
    Prev
    Next
    INDEX
    Explanations

    references to councils or committees involved in governance or decision-making processes

    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
     pinulongan
    -0.42
     centres
    -0.40
     emas
    -0.35
     hObject
    -0.33
     onDestroy
    -0.33
     onFailure
    -0.33
     centred
    -0.32
    jano
    -0.32
    grü
    -0.32
     vira
    -0.32
    POSITIVE LOGITS
     Council
    1.18
    council
    1.14
     council
    1.14
    Council
    1.09
     COUNCIL
    1.03
     counsel
    0.82
     Center
    0.82
     Counsel
    0.79
    UNCIL
    0.79
     Councils
    0.76
    Activations Density 0.114%

    No Known Activations