© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4195
    Prev
    Next
    INDEX
    Explanations

    phrases related to wandering or movement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.30
    1.2%
    752
    +0.13
    0.5%
    1810
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.30
    0.05
    51
    +0.13
    0.03
    752
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.14
    lateinit
    -0.63
    /***
    -0.62
    continue
    -0.59
     continue
    -0.59
    //----
    -0.57
    /**
    -0.57
    catch
    -0.57
     caught
    -0.55
     get
    -0.53
    POSITIVE LOGITS
     délib
    1.29
     Juf
    1.24
     swarovski
    1.23
     vété
    1.19
     considér
    1.18
     mépris
    1.18
     véhic
    1.16
     soulign
    1.14
     malheureux
    1.13
     écout
    1.11
    Activations Density 0.355%

    No Known Activations