© 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. 16-GEMMASCOPE-RES-16K
    6. 5365
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses related to various sources and categories

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

    URLs

    np_acts-logits-general · gemini-2.0-flash

    URLs ending in slash

    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
     <=",
    -0.66
    UrlResolution
    -0.65
    PreferredItem
    -0.57
    PerformLayout
    -0.55
    uxxxx
    -0.54
    AnchorStyles
    -0.53
    principalTable
    -0.53
    insee
    -0.52
    ichord
    -0.52
     محفوظة
    -0.52
    POSITIVE LOGITS
    ]--;
    0.64
    index
    0.55
     Alva
    0.50
    PostMapping
    0.49
    ophil
    0.49
     imageNamed
    0.49
     website
    0.48
    (`/
    0.48
     Magdal
    0.48
    ptian
    0.48
    Activations Density 0.082%

    No Known Activations