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. 25-GEMMASCOPE-RES-16K
    6. 461
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and algorithm implementation

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

    concepts related to programming logic and implementation details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.58
     kasarigan
    -0.54
     ?>>
    -0.50
    ngdoc
    -0.50
    ')")
    -0.50
    Rüyada
    -0.50
    }?>
    -0.48
    GEBURTSDATUM
    -0.48
     appartient
    -0.47
    );?>
    -0.47
    POSITIVE LOGITS
     iterate
    0.96
     iter
    0.86
     looping
    0.81
     Iterate
    0.78
     traversing
    0.77
     loop
    0.76
     iteration
    0.74
     scanning
    0.73
     traverses
    0.72
     loops
    0.72
    Activations Density 0.908%

    No Known Activations