© 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. 30-GEMMASCOPE-RES-16K
    11. 12533
    Prev
    Next
    INDEX
    Explanations

    research studies focusing on examining and investigating various effects and relationships

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

    "The" followed by a word related to impact or effect

    np_acts-logits-general · gemini-2.0-flash

    effect, impact, potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ControllerBase
    -0.39
    formKey
    -0.35
     faltar
    -0.34
     Grüsse
    -0.32
    whitelist
    -0.31
     ficando
    -0.31
     напомина
    -0.30
     hätten
    -0.30
    เว
    -0.30
    zeti
    -0.30
    POSITIVE LOGITS
     effect
    1.53
     effects
    1.51
     influence
    1.43
     Effect
    1.36
    Effect
    1.34
    effect
    1.31
     impact
    1.30
     Effects
    1.30
    Effects
    1.28
     Influence
    1.25
    Activations Density 2.048%

    No Known Activations