© 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. 9642
    Prev
    Next
    INDEX
    Explanations

    lines of code related to object manipulation and management functions

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

    Code snippets using "bool", "ui", and "*" variables

    np_acts-logits-general · gemini-2.0-flash

    bool or creature ui

    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
    ,
    -0.53
    -
    -0.52
     
    -0.52
    .
    -0.50
    :
    -0.44
     —
    -0.42
    /
    -0.42
     er
    -0.40
    مس
    -0.40
     T
    -0.39
    POSITIVE LOGITS
     disambiguazione
    1.02
    SourceChecksum
    1.01
     Efq
    1.00
     Theſe
    1.00
     protoimpl
    0.98
     myſelf
    0.97
    expandindo
    0.97
    AddTagHelper
    0.94
     becauſe
    0.93
    NameInMap
    0.92
    Activations Density 0.238%

    No Known Activations