© 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. 4409
    Prev
    Next
    INDEX
    Explanations

    phrases indicating attribution or causation

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

    "part" or "due" followed by preposition

    np_acts-logits-general · gemini-2.0-flash

    due, in part, to

    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
     Roskov
    -0.65
    ządu
    -0.64
     onCreateView
    -0.60
     مشين
    -0.59
     Efq
    -0.57
    ]")]
    -0.56
    subpackage
    -0.55
    getSeconds
    -0.54
     MotionEvent
    -0.54
     Signalez
    -0.53
    POSITIVE LOGITS
     partly
    2.27
    partly
    1.99
     Partly
    1.86
     largely
    1.72
     part
    1.64
     partially
    1.62
    Partly
    1.61
     mainly
    1.52
    part
    1.52
    Part
    1.49
    Activations Density 0.397%

    No Known Activations