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. 6186
    Prev
    Next
    INDEX
    Explanations

    directory paths and file structure references in programming or shell commands

    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
     nakalista
    -0.57
    WillAppear
    -0.56
    APORE
    -0.52
    "]);
    
    -0.50
     “...
    -0.50
    ConstraintMaker
    -0.49
    multirow
    -0.49
     disambiguazione
    -0.49
    DrawerToggle
    -0.47
    batross
    -0.47
    POSITIVE LOGITS
     referenties
    0.72
    memoized
    0.64
    HideFlags
    0.63
     CWE
    0.63
    الحياه
    0.62
    NameInMap
    0.60
    PropertyChanging
    0.60
     dinas
    0.59
     aDecoder
    0.59
     BoxFit
    0.58
    Activations Density 0.245%

    No Known Activations