© 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. 3260
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation

    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
    +0.23
    1.0%
    382
    +0.18
    0.8%
    331
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.23
    0.05
    331
    +0.18
    0.05
    1445
    +0.13
    0.05
    Negative Logits
    <bos>
    -2.75
     intersper
    -1.15
    ⓧ
    -1.05
     reconno
    -1.02
     endow
    -0.99
    /**
    -0.98
     rouse
    -0.98
     quitted
    -0.95
     vainly
    -0.95
     rascal
    -0.93
    POSITIVE LOGITS
     seksi
    1.28
     silikon
    1.21
     keramik
    1.17
     maksi
    1.17
     kafe
    1.14
     lemp
    1.13
     karton
    1.11
     teras
    1.09
     mikrofon
    1.09
     kokos
    1.08
    Activations Density 0.078%

    No Known Activations