© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4577
    Prev
    Next
    INDEX
    Explanations

    mentions or instances of verbs related to movement or action, specifically the act of jumping

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1805
    +0.12
    0.4%
    1562
    +0.12
    0.4%
    690
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1805
    +0.12
    0.03
    1562
    +0.12
    0.03
    537
    +0.10
    0.03
    Negative Logits
    儡
    -0.49
    Jährige
    -0.47
    AccessorTable
    -0.46
    RTEE
    -0.45
    setAlignment
    -0.45
    SceneManagement
    -0.44
    rencies
    -0.44
    Mediabestanden
    -0.44
    ņi
    -0.43
    égias
    -0.43
    POSITIVE LOGITS
     jump
    1.25
     JUMP
    1.23
    jump
    1.20
     jumps
    1.13
     jumping
    1.12
     Jump
    1.11
     jumped
    1.09
    Jump
    1.09
     Jumping
    1.08
    jumps
    1.07
    Activations Density 0.089%

    No Known Activations