© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13806
    Prev
    Next
    INDEX
    Explanations

    phrases related to education and communication in a classroom setting

    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
    1150
    +0.13
    0.4%
    453
    +0.11
    0.3%
    1314
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.13
    0.07
    1415
    +0.11
    0.02
    1889
    +0.08
    0.04
    Negative Logits
     swarovski
    -1.28
     hairc
    -1.25
     increa
    -1.24
     guarante
    -1.21
     encomp
    -1.19
     affor
    -1.18
     disagre
    -1.16
     hilux
    -1.15
     scrat
    -1.15
     tupperware
    -1.14
    POSITIVE LOGITS
    <bos>
    0.97
     information
    0.70
     ProtoMessage
    0.70
    information
    0.68
    SourceChecksum
    0.67
     Paglinawan
    0.64
     discussion
    0.63
     reporting
    0.63
    ieteur
    0.63
     informative
    0.63
    Activations Density 0.881%

    No Known Activations