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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10905
    Prev
    Next
    INDEX
    Explanations

    code-related functions and their structure

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

    ending in "ic"

    np_acts-logits-general · gemini-2.0-flash

    ic acid extraction

    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
    Datuak
    -0.84
    CodedInputStream
    -0.81
     unknownFields
    -0.70
     estekak
    -0.69
    ={()=>
    -0.68
    TagHelpers
    -0.67
    NavController
    -0.66
    ({_
    -0.64
     EClass
    -0.62
     propOrder
    -0.62
    POSITIVE LOGITS
     XNUMX
    0.73
     myſelf
    0.58
     itſelf
    0.56
    Abit
    0.55
    .)}
    0.55
     //
    0.54
     ſeveral
    0.53
    .")]
    0.53
     ***/
    0.53
     ""}
    0.51
    Activations Density 0.364%

    No Known Activations