© 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. 14-GEMMASCOPE-RES-16K
    6. 9324
    Prev
    Next
    INDEX
    Explanations

    phrases related to hope and future aspirations 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 @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -1.11
     Paglinawan
    -1.10
     تكبرها
    -0.97
    WithIOException
    -0.96
    __':
    
    -0.94
    SourceChecksum
    -0.92
    __":
    
    -0.89
    __':
    -0.89
    protoimpl
    -0.89
     Signalez
    -0.88
    POSITIVE LOGITS
     or
    0.55
    ↵↵↵
    0.53
    <eos>
    0.52
     xong
    0.49
    ↵↵↵↵↵
    0.48
     and
    0.47
     home
    0.47
     because
    0.45
     -
    0.43
    destroyAll
    0.43
    Activations Density 0.467%

    No Known Activations