© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1689
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a direction or movement towards a goal

    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
    1265
    +0.19
    1.1%
    897
    +0.16
    0.9%
    1328
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.19
    0.03
    1328
    +0.16
    0.03
    897
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.51
     organise
    -0.65
     prioritise
    -0.65
     TDA
    -0.64
     realise
    -0.62
     realises
    -0.62
     summarise
    -0.62
     optimise
    -0.62
     maximise
    -0.61
     emphasise
    -0.60
    POSITIVE LOGITS
    requently
    0.92
     Settembre
    0.87
    havior
    0.86
     autunno
    0.86
    toward
    0.85
     montagna
    0.85
     vacanza
    0.84
    UREAU
    0.84
     signora
    0.83
     Karang
    0.83
    Activations Density 0.253%

    No Known Activations