© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6961
    Prev
    Next
    INDEX
    Explanations

    references to goals and goal-setting concepts

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

    "goal" or "goals"

    np_acts-logits-general · gemini-2.0-flash

    goal-setting and aims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ührt
    -0.49
    readFileSync
    -0.42
     vice
    -0.42
    existsSync
    -0.41
    জন
    -0.41
    s
    -0.41
    netinet
    -0.39
    en
    -0.39
     käyt
    -0.39
    ņas
    -0.39
    POSITIVE LOGITS
     GOAL
    0.99
     Goals
    0.97
    GOAL
    0.96
    Goals
    0.92
     Goal
    0.90
    DispatchToProps
    0.90
     goals
    0.87
     Eſ
    0.87
     GOALS
    0.85
    InstanceState
    0.84
    Activations Density 0.186%

    No Known Activations