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. 18-GEMMASCOPE-RES-16K
    6. 558
    Prev
    Next
    INDEX
    Explanations

    terms associated with programming constructs and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, data types, or database fields

    np_acts-logits-general · gemini-2.0-flash

    column, :, with, then, =, ., ], for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ")));
    
    -1.06
    ]));
    
    -1.06
    "]));
    -1.03
    )");
    
    -0.99
    ]))
    
    -0.97
    )";
    
    -0.97
    "])
    
    -0.96
    )++;
    -0.96
    WebElementEntity
    -0.96
    ."]
    -0.94
    POSITIVE LOGITS
    _
    0.83
    ()
    0.75
    .
    0.57
    []
    0.53
    _{
    0.53
    ->
    0.53
    ().
    0.53
     is
    0.53
    (),
    0.51
    が
    0.51
    Activations Density 1.127%

    No Known Activations