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. 16-GEMMASCOPE-RES-16K
    6. 1584
    Prev
    Next
    INDEX
    Explanations

    file path segments or identifiers commonly used in programming or markup languages

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

    Code or file paths

    np_acts-logits-general · gemini-2.0-flash

    Trail, density, blood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.90
     }));
    -0.64
    ."));
    -0.64
    )))));
    -0.58
    ţilor
    -0.56
    )});
    -0.56
     Ici
    -0.55
     }}</
    -0.55
    })]
    -0.55
    :✨
    -0.55
    POSITIVE LOGITS
    — 
    0.73
     OFDb
    0.68
    StructEnd
    0.63
    ">//
    0.60
     useState
    0.60
     bVar
    0.60
     AppCompat
    0.55
    extAlignment
    0.55
    PyExc
    0.55
    ioutil
    0.53
    Activations Density 0.022%

    No Known Activations