© 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. 5-GEMMASCOPE-RES-16K
    11. 9579
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to false positives and errors in diagnoses or legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.54
    vités
    -0.51
     clearly
    -0.44
    carpus
    -0.42
    dibles
    -0.42
    }")
    -0.41
    WritableDatabase
    -0.41
    ьаж
    -0.40
    :]:
    -0.40
    NamedQueries
    -0.40
    POSITIVE LOGITS
     prematurely
    0.80
     unnecessarily
    0.71
    HostException
    0.70
    yntaxException
    0.70
     wrongly
    0.70
     برانيه
    0.69
     raiſ
    0.68
     wireType
    0.68
     improperly
    0.67
     Houſe
    0.65
    Activations Density 0.575%

    No Known Activations