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. 14648
    Prev
    Next
    INDEX
    Explanations

    specific named entities and technical terms in various domains

    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
    igshid
    -0.72
     TestBed
    -0.65
     disambiguazione
    -0.63
     跳转至
    -0.62
     ainfi
    -0.61
    },{
    
    -0.60
     utafitiHapana
    -0.60
     مشين
    -0.59
    المكان
    -0.59
     تضيفلها
    -0.59
    POSITIVE LOGITS
    TagMode
    0.52
     taget
    0.47
    wieś
    0.46
     phẩm
    0.46
    enterOuterAlt
    0.45
     AssemblyVersion
    0.44
    일에
    0.42
    `*)
    0.39
    `)
    0.39
     bound
    0.39
    Activations Density 0.705%

    No Known Activations