© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 16118
    Prev
    Next
    INDEX
    Explanations

    mentions of technical issues or problems related to software or programming contexts

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

    after a short word

    np_acts-logits-general · gemini-2.0-flash

    city names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    KommentareTeilen
    -0.71
    +#+#
    -0.58
    ̍t
    -0.57
    protoimpl
    -0.55
     SCS
    -0.54
     assister
    -0.54
     跳转至
    -0.53
    OGND
    -0.53
     متعلقه
    -0.52
    TemporalType
    -0.52
    POSITIVE LOGITS
    Fecha
    0.54
    arkhand
    0.49
     bè
    0.44
    FRAME
    0.43
    들에게
    0.43
    führung
    0.42
    anzibar
    0.42
     Fecha
    0.42
     bê
    0.42
     rasgos
    0.42
    Activations Density 0.071%

    No Known Activations