© 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-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14708
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulties, problems, or challenges in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
     Vordergrund
    -0.46
    sandalia
    -0.46
     regalías
    -0.44
     împre
    -0.43
     Offisielt
    -0.43
    ælp
    -0.43
     argint
    -0.43
     ModelExpression
    -0.42
     invitaciones
    -0.42
    trás
    -0.42
    POSITIVE LOGITS
     because
    1.11
     omdat
    0.83
    because
    0.82
     porque
    0.80
     karena
    0.77
     потому
    0.75
     Because
    0.75
    Because
    0.74
    因为
    0.71
    因為
    0.70
    Activations Density 0.724%

    No Known Activations