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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14790
    Prev
    Next
    INDEX
    Explanations

    verbs associated with construction, achievement, and demonstration of success

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

    Verb followed by a pronoun/article

    np_acts-logits-general · gemini-2.0-flash

    past tense actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vzduchu
    -0.75
     HasFactory
    -0.70
     Hesper
    -0.65
    enumi
    -0.64
    fact
    -0.62
     CPF
    -0.58
    fillType
    -0.58
    antMatchers
    -0.57
    FACT
    -0.57
    exitRule
    -0.57
    POSITIVE LOGITS
     ayer
    0.79
     nakalista
    0.78
     went
    0.77
    Personendaten
    0.77
     began
    0.77
     gave
    0.77
    }}}
    
    0.76
     wrote
    0.75
    =$?
    0.75
     drove
    0.73
    Activations Density 0.745%

    No Known Activations