Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12167
    Prev
    Next
    INDEX
    Explanations

    terms related to challenges or difficulties in various contexts

    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
     comerciais
    -0.53
    गु
    -0.51
    пьютер
    -0.50
     sighing
    -0.45
    Hz
    -0.45
    buje
    -0.45
    zeug
    -0.45
     déri
    -0.44
    죄
    -0.44
     nacionais
    -0.44
    POSITIVE LOGITS
     faced
    1.20
     posed
    1.19
    Challenges
    1.02
     challenges
    1.00
     Faced
    0.99
     تضيفلها
    0.99
     Challenges
    0.97
    challenges
    0.92
    faced
    0.92
     facing
    0.90
    Activations Density 0.081%

    No Known Activations