© 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. 9506
    Prev
    Next
    INDEX
    Explanations

    specific names of individuals and their titles or roles

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

    Tokens before "is"

    np_acts-logits-general · gemini-2.0-flash

    names followed by descriptions

    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
    MigrationBuilder
    -1.42
    NUMX
    -1.37
     Мексичка
    -1.36
    ^(@)
    -1.35
     ་་
    -1.34
     Савезне
    -1.31
     $_"
    -1.26
     photolibrary
    -1.24
     tslint
    -1.22
     '\\;'
    -1.21
    POSITIVE LOGITS
    <eos>
    1.44
    ↵↵
    1.40
    ↵
    1.30
    :
    1.25
     is
    1.20
     
    1.13
     -
    1.10
     |
    1.06
     has
    1.01
     was
    1.00
    Activations Density 1.487%

    No Known Activations