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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3256
    Prev
    Next
    INDEX
    Explanations

    adjectives that imply certainty or unchangeability

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

    ending in "-bly", "-sibly", "-uble", or "imaginable"

    np_acts-logits-general · gemini-2.0-flash

    unstoppable, undeniable, inevitable

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    
    -0.77
    +#+
    -0.69
    aarrggbb
    -0.66
    oneofs
    -0.66
    ScopeManager
    -0.63
    IBOutlet
    -0.61
    SequentialGroup
    -0.61
    PhysRevD
    -0.58
    writeFieldEnd
    -0.58
     wikipagina
    -0.57
    POSITIVE LOGITS
     unstoppable
    0.75
     undeniable
    0.73
     inevitable
    0.68
     inescapable
    0.67
     unbeatable
    0.67
     unavoidable
    0.67
     immutable
    0.62
     indisputable
    0.62
     indestructible
    0.61
     insurmountable
    0.60
    Activations Density 0.338%

    No Known Activations