Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 1343
    Prev
    Next
    INDEX
    Explanations

    academic settings and educational activities involving students and instructors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )$/,
    -0.59
    RectangleBorder
    -0.57
    posedge
    -0.54
    .}\
    -0.53
    </thead>
    -0.53
     '))
    -0.52
    rungsseite
    -0.52
    ")));
    -0.51
    ')).
    -0.51
    ']>;
    -0.51
    POSITIVE LOGITS
     classroom
    1.03
     professors
    0.93
     teacher
    0.93
     Classroom
    0.92
     classrooms
    0.91
     teachers
    0.90
     Teacher
    0.85
     students
    0.85
     teaching
    0.84
    teacher
    0.83
    Activations Density 0.160%

    No Known Activations