© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7376
    Prev
    Next
    INDEX
    Explanations

    references to sensitive or critical information involving technology and communications

    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
     betweenstory
    -0.93
    UnusedPrivate
    -0.81
    tonode
    -0.76
     BoxFit
    -0.76
    AnchorStyles
    -0.75
    Бахар
    -0.74
     tartalomajánló
    -0.72
     endwhile
    -0.71
    ArgsConstructor
    -0.71
    InjectAttribute
    -0.71
    POSITIVE LOGITS
    MessageDigest
    0.57
     ion
    0.50
     chemically
    0.46
    date
    0.42
     yıllar
    0.40
    aine
    0.39
    jni
    0.39
    STRU
    0.39
     newState
    0.38
    agens
    0.38
    Activations Density 1.162%

    No Known Activations