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

    Neuronpedia

    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. 4-GEMMASCOPE-RES-16K
    11. 1099
    Prev
    Next
    INDEX
    Explanations

    repeated sequences of dashes or lines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     heapq
    -0.75
    »)
    -0.74
    ]),
    -0.73
     Audiodateien
    -0.72
    "}")
    -0.72
    intellij
    -0.70
    bondale
    -0.70
    »).
    -0.70
    °)
    -0.69
    ReusableCell
    -0.69
    POSITIVE LOGITS
    ----------------
    2.55
    ---------------
    1.75
    --------------
    1.41
    ------------
    1.35
    -------------
    1.26
    -----------
    1.23
    --------
    1.20
    ---------
    1.11
    -------
    1.09
     ---------------
    1.08
    Activations Density 0.214%

    No Known Activations