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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15369
    Prev
    Next
    INDEX
    Explanations

    phrases related to achieving goals or overcoming challenges

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

    "it" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    make it through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.80
     Jefus
    -0.76
     pleaſure
    -0.76
    httphttps
    -0.74
     myſelf
    -0.74
    tagHelperRunner
    -0.70
    ſelf
    -0.68
     Houſe
    -0.68
     ſy
    -0.68
     Chrift
    -0.68
    POSITIVE LOGITS
     into
    0.94
     through
    0.80
     onto
    0.71
     INTO
    0.65
     past
    0.64
     across
    0.63
     back
    0.62
     nowhere
    0.61
    through
    0.59
     Into
    0.58
    Activations Density 0.087%

    No Known Activations