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. 7-GEMMASCOPE-RES-16K
    6. 6124
    Prev
    Next
    INDEX
    Explanations

    transitions and markers in written content that indicate a change in topic or focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Insee
    -0.45
    Anywhere
    -0.44
    antlr
    -0.44
    <eos>
    -0.43
     corso
    -0.42
     Insee
    -0.41
    atissimo
    -0.40
     aeruginosa
    -0.40
     scheda
    -0.39
     resourceCulture
    -0.38
    POSITIVE LOGITS
    Portale
    0.79
     насељу
    0.68
    pushFollow
    0.67
    expandindo
    0.66
     article
    0.66
    RenderAtEndOf
    0.65
    __':
    
    0.65
     Савезне
    0.63
     esternos
    0.62
     ExecuteAsync
    0.62
    Activations Density 0.292%

    No Known Activations