© 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. 11023
    Prev
    Next
    INDEX
    Explanations

    instances of the word "even" and expressions of personal opinions

    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
    crollView
    -0.71
     @"";
    -0.68
    RuleContext
    -0.66
    DockStyle
    -0.65
     numberOfRows
    -0.61
     BaseActivity
    -0.60
    ISupport
    -0.59
    }]);
    -0.58
    AutoresizingMask
    -0.58
     widest
    -0.58
    POSITIVE LOGITS
     even
    1.07
     sogar
    1.04
     addirittura
    0.94
     Even
    0.86
     EVEN
    0.82
    even
    0.81
    Even
    0.79
     zelfs
    0.78
     persino
    0.78
     даже
    0.74
    Activations Density 0.128%

    No Known Activations