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. 15-GEMMASCOPE-RES-16K
    6. 8572
    Prev
    Next
    INDEX
    Explanations

    elements related to coding and software components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ʐ
    -0.64
     Donahue
    -0.64
    yanto
    -0.60
    TableHead
    -0.59
    subsec
    -0.58
     persil
    -0.57
     IEnumerator
    -0.55
    ulement
    -0.54
    ʑ
    -0.54
     Withers
    -0.54
    POSITIVE LOGITS
    })()
    1.02
    ]";
    0.99
    ]]);
    0.99
    ])));
    0.97
    ')));
    0.94
    ())));
    0.94
    })();
    
    0.94
    ']));
    0.93
    /';
    0.93
    ;';
    0.91
    Activations Density 0.007%

    No Known Activations