© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5335
    Prev
    Next
    INDEX
    Explanations

    references to companies and their business activities

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

    descriptions or systems

    np_acts-logits-general · gemini-2.0-flash

    describing status or responsibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.55
    VolleyError
    -0.52
    Diweddarwch
    -0.51
    舺
    -0.49
     &___
    -0.49
    AddTagHelper
    -0.49
     ब्रेकडाउन
    -0.49
    kuuta
    -0.43
    كويكب
    -0.42
    AnimationsModule
    -0.42
    POSITIVE LOGITS
     description
    0.45
     aimed
    0.45
     describing
    0.42
    description
    0.42
     describes
    0.42
    负责
    0.42
    Description
    0.41
    responsible
    0.40
    desc
    0.40
     responsible
    0.40
    Activations Density 0.849%

    No Known Activations