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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103126
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to ineffective assistance of counsel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Legal terminology regarding "ineffective assistance of counsel" claims in post-conviction proceedings, appearing alongside various domain-specific technical terms in programming, scientific research, and statistical analysis contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    IntoConstraints
    -1.12
    хьтан
    -0.65
     فريبيس
    -0.64
    ConstraintMaker
    -0.64
    setViewportView
    -0.63
     defaultstate
    -0.63
    DockStyle
    -0.60
    AnchorStyles
    -0.59
    лтамалар
    -0.58
    ↹
    -0.57
    POSITIVE LOGITS
    transQ
    0.42
     brancas
    0.40
    tagHelperRunner
    0.37
     fortæ
    0.35
    Ӕ
    0.34
    anglès
    0.34
    Gson
    0.34
     bandoulière
    0.34
    bcryptjs
    0.33
    wnia
    0.33
    Activations Density 26.913%

    No Known Activations