© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1090
    Prev
    Next
    INDEX
    Explanations

    relationships and familial connections

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

    Comes after "of" or "to"

    np_acts-logits-general · gemini-2.0-flash

    parents' names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wäh
    -0.46
    saco
    -0.46
     dure
    -0.43
    otro
    -0.41
     hech
    -0.41
     Sandro
    -0.41
     novi
    -0.41
    derry
    -0.41
     bof
    -0.41
    ̣n
    -0.40
    POSITIVE LOGITS
    farwyddwr
    0.72
     genitori
    0.72
     centenary
    0.72
     BoxFit
    0.69
     unknownFields
    0.68
    AccessorTable
    0.68
    ArgsConstructor
    0.67
    Geplaatst
    0.67
     endregion
    0.66
    WarningLevel
    0.65
    Activations Density 0.031%

    No Known Activations