© 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. 22-GEMMASCOPE-RES-16K
    11. 6233
    Prev
    Next
    INDEX
    Explanations

    terms related to data management and storage

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

    Chinese or Japanese characters

    np_acts-logits-general · gemini-2.0-flash

    儲存／備份／訂閱／篩選

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rather
    -0.48
    Rather
    -0.44
    Pronunciation
    -0.42
    Zubereitung
    -0.42
    GENERATED
    -0.41
    벳
    -0.41
    rather
    -0.40
     capital
    -0.40
    萌
    -0.40
     courriel
    -0.40
    POSITIVE LOGITS
     nakalista
    0.71
    wußt
    0.69
     Phoen
    0.68
    enumii
    0.67
     ſtate
    0.64
    enumi
    0.64
     cauſe
    0.61
     ſche
    0.59
     hierogly
    0.59
    zebra
    0.58
    Activations Density 0.209%

    No Known Activations