© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2440
    Prev
    Next
    INDEX
    Explanations

    terms related to the purpose and aim of studies or interventions

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

    the word "The" at the beginning of research paper sections and objective statements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PhysRevLett
    -0.40
    الإنجليزية
    -0.40
     autorytatywna
    -0.40
    Koordinaten
    -0.40
    quiao
    -0.39
    getColumnIndex
    -0.39
    ray
    -0.38
    getWriter
    -0.37
    tauan
    -0.37
    entikan
    -0.37
    POSITIVE LOGITS
     purpose
    2.72
     aim
    2.41
    Purpose
    2.16
     goal
    2.16
     Purpose
    2.14
    purpose
    2.11
    目的
    2.08
     tujuan
    2.00
     aims
    2.00
     PURPOSE
    1.99
    Activations Density 0.789%

    No Known Activations