© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11101
    Prev
    Next
    INDEX
    Explanations

    objectives and goals related to projects or studies

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

    "goal" or "objectives" and subsequent purpose

    np_acts-logits-general · gemini-2.0-flash

    objective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.65
    adpleegd
    -0.54
    Erreferentziak
    -0.52
    detectChanges
    -0.51
    knex
    -0.49
    ulance
    -0.47
     linkovi
    -0.47
     protoimpl
    -0.47
    ements
    -0.47
     bParam
    -0.46
    POSITIVE LOGITS
     objectives
    1.42
     goals
    1.41
     objectifs
    1.36
     objetivos
    1.26
     Objectives
    1.25
    Objectives
    1.24
     goal
    1.24
     Goals
    1.22
    Goals
    1.21
     OBJECTIVES
    1.20
    Activations Density 0.513%

    No Known Activations