© 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. 22-GEMMASCOPE-RES-16K
    6. 3069
    Prev
    Next
    INDEX
    Explanations

    phrases or words that imply continuation or accompaniment

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

    "Along with" phrase

    np_acts-logits-general · gemini-2.0-flash

    along with

    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
    esez
    -0.56
    <bos>
    -0.55
     hoạch
    -0.55
    apolis
    -0.53
    tifice
    -0.53
     microm
    -0.53
     teken
    -0.50
    emia
    -0.50
    ulario
    -0.49
     aeruginosa
    -0.49
    POSITIVE LOGITS
     along
    0.84
    side
    0.82
     ALONG
    0.79
    SIDE
    0.79
     side
    0.78
    sides
    0.77
    AutoresizingMask
    0.76
    Along
    0.72
    shore
    0.71
    along
    0.71
    Activations Density 0.051%

    No Known Activations