© 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 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. 14706
    Prev
    Next
    INDEX
    Explanations

    syntax elements and programming language keywords

    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
    468
    +0.14
    0.4%
    1081
    +0.12
    0.4%
    1842
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.14
    0.01
    1081
    +0.12
    0.04
    1045
    +0.11
    0.03
    Negative Logits
    Estat
    -0.56
     Sha
    -0.56
    Atra
    -0.54
     Inter
    -0.53
     Al
    -0.51
     Ten
    -0.51
     En
    -0.50
    Enf
    -0.50
    Perú
    -0.49
     Tal
    -0.49
    POSITIVE LOGITS
     milf
    1.19
    fordable
    1.16
     curé
    1.11
     bandung
    1.10
     gmbh
    1.08
     bordeaux
    1.06
     fluo
    1.04
     affez
    1.03
     Docteur
    1.03
     broderie
    1.02
    Activations Density 0.205%

    No Known Activations