© 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. 5980
    Prev
    Next
    INDEX
    Explanations

    references to historical fortifications and military structures

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

    relating to defense structures and security

    np_acts-logits-general · gemini-2.0-flash

    security barriers and passwords

    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
     CreateTagHelper
    -0.60
    onViewCreated
    -0.54
    etzal
    -0.53
     صوتيه
    -0.53
    XmlType
    -0.51
     typelib
    -0.48
    avoie
    -0.47
    ⓧ
    -0.47
    ReusableCell
    -0.46
    geber
    -0.46
    POSITIVE LOGITS
     walls
    1.25
     fence
    1.17
     fortifications
    1.16
     fortification
    1.15
     wall
    1.13
     fences
    1.11
     defences
    1.09
     walled
    1.09
     Walls
    1.08
     defenses
    1.06
    Activations Density 0.142%

    No Known Activations