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. 14-GEMMASCOPE-RES-16K
    6. 139
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations or places

    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
    تفصیلات
    -1.07
     **/
    
    -0.94
    HttpHeaders
    -0.93
    ↴
    -0.92
    WithIOException
    -0.91
     scolaires
    -0.89
     ")");
    -0.89
     meningitis
    -0.88
    ]))
    
    -0.88
    ]));
    
    -0.87
    POSITIVE LOGITS
     place
    1.32
     PLACE
    1.28
    Place
    1.28
    place
    1.27
     Place
    1.24
    PLACE
    1.20
     places
    1.13
    places
    1.11
    Places
    1.10
     Places
    1.06
    Activations Density 0.047%

    No Known Activations