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. 17-GEMMASCOPE-RES-16K
    6. 1115
    Prev
    Next
    INDEX
    Explanations

    locations and spatial descriptors in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])).
    -0.82
    цездатний
    -0.69
    soever
    -0.68
    SequentialGroup
    -0.65
    %]
    -0.65
    ]));
    
    -0.63
     дописавши
    -0.62
    ")));
    
    -0.62
    )))));
    -0.60
    "]));
    -0.60
    POSITIVE LOGITS
     looking
    0.61
     adjacent
    0.58
     viewDidLoad
    0.57
     overlooking
    0.56
     opposite
    0.55
     olhando
    0.54
     adjoining
    0.52
     upstairs
    0.51
    tonode
    0.50
     rafters
    0.50
    Activations Density 0.221%

    No Known Activations