© 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. 3700
    Prev
    Next
    INDEX
    Explanations

    terms related to advocacy or promotional campaigns

    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
    2034
    +0.16
    0.5%
    1150
    +0.15
    0.5%
    1013
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.16
    0.08
    1013
    +0.15
    0.08
    74
    +0.15
    0.05
    Negative Logits
     fta
    -1.33
     „,
    -1.32
     aen
    -1.30
     ftu
    -1.24
     doman
    -1.24
     fep
    -1.21
     blos
    -1.21
     meis
    -1.15
     fup
    -1.15
     fte
    -1.14
    POSITIVE LOGITS
     involving
    0.86
     featuring
    0.67
     consisting
    0.66
     aimed
    0.64
     whose
    0.62
     which
    0.61
     centered
    0.60
     wherein
    0.60
     reminiscent
    0.60
     whereby
    0.59
    Activations Density 0.563%

    No Known Activations