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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 65807
    Prev
    Next
    INDEX
    Explanations

    object types and data structures commonly used in programming, particularly in frameworks like iOS and .NET

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vergrößern
    -0.52
    ArgsConstructor
    -0.49
    BindView
    -0.48
    ∎
    -0.42
     pleaſure
    -0.42
    ckså
    -0.42
     listo
    -0.42
     varandra
    -0.41
    tabular
    -0.41
     싶
    -0.41
    POSITIVE LOGITS
     CGRect
    1.73
    CGRect
    1.34
     CGSize
    1.20
     CGPoint
    1.13
    CGPoint
    0.85
    CGSize
    0.85
     MotionEvent
    0.69
    CGRectMake
    0.60
     CGFloat
    0.59
     mxArray
    0.57
    Activations Density 0.002%

    No Known Activations