© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14170
    Prev
    Next
    INDEX
    Explanations

    terms related to government agencies and departments involved in regulation and oversight

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

    Governmental departments or agencies

    np_acts-logits-general · gemini-2.0-flash

    government departments and services

    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
    IsMutable
    -0.70
    }}_{\
    -0.60
    MigrationBuilder
    -0.58
    }}_
    -0.58
    AddTagHelper
    -0.58
    //</
    -0.54
    dagogik
    -0.54
    AlterField
    -0.53
    }}_{
    -0.53
    مصادر
    -0.51
    POSITIVE LOGITS
     department
    0.75
     dept
    0.64
     ModelExpression
    0.57
     estekak
    0.57
    ESO
    0.55
    department
    0.54
    iços
    0.52
    dept
    0.51
     tsar
    0.51
     authorities
    0.51
    Activations Density 0.252%

    No Known Activations