Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 14750
    Prev
    Next
    INDEX
    Explanations

    sections and their organization within a paper

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     True
    -0.50
    randrange
    -0.47
    True
    -0.47
    XmlAccessType
    -0.43
    اعي
    -0.42
    fect
    -0.42
    Fuckin
    -0.41
    iguar
    -0.41
    bcryptjs
    -0.40
    favicon
    -0.40
    POSITIVE LOGITS
    expandindo
    0.90
    abestanden
    0.86
    InstanceState
    0.81
    __":
    
    0.80
     }}"></
    0.79
    lgari
    0.77
    __':
    
    0.77
    ValueStyle
    0.76
    DotNetBar
    0.75
    initComponents
    0.72
    Activations Density 0.495%

    No Known Activations