© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8285
    Prev
    Next
    INDEX
    Explanations

    terms related to the development and functioning of medical and health-related systems

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

    preceding "of" related to development or processes

    np_acts-logits-general · gemini-2.0-flash

    emergence, induction, formation, development, generation, maintenance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -1.01
     snippetHide
    -0.81
    latego
    -0.80
     <<<<<<<<<<<<<<
    -0.80
    ConstraintMaker
    -0.78
    <?
    -0.77
    DockStyle
    -0.77
     صوتيه
    -0.74
    +#+#
    -0.74
     myſelf
    -0.74
    POSITIVE LOGITS
     stesso
    0.45
     certain
    0.45
     bzw
    0.43
    _^
    0.39
     illetve
    0.39
     of
    0.38
    getMenuInflater
    0.38
     or
    0.38
    起的
    0.38
     apellidos
    0.37
    Activations Density 0.541%

    No Known Activations