© 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. 23-GEMMASCOPE-RES-16K
    6. 9171
    Prev
    Next
    INDEX
    Explanations

    words with the letter 'f' and variations of that letter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.55
     intptr
    -0.53
     verrez
    -0.52
    SetInt
    -0.47
    substack
    -0.46
    曖昧さ回避
    -0.46
    asable
    -0.45
    ACHE
    -0.45
    ICHE
    -0.44
    游戏亮点
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.97
    FormTagHelper
    0.77
     HasFactory
    0.71
    WebElementEntity
    0.66
    DataAnnotations
    0.62
    MLLoader
    0.60
     iprot
    0.58
    LookAnd
    0.57
    ]")]
    0.55
     Kome
    0.54
    Activations Density 0.237%

    No Known Activations