© 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. 13775
    Prev
    Next
    INDEX
    Explanations

    references to music albums and songs

    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
    1978
    +0.13
    0.4%
    690
    +0.12
    0.4%
    764
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1177
    +0.13
    0.02
    981
    +0.12
    0.05
    1902
    +0.12
    0.03
    Negative Logits
    <bos>
    -0.79
     Paglinawan
    -0.77
    хьтан
    -0.68
     ujednoznacz
    -0.67
    Aholisi
    -0.67
     تضيفلها
    -0.66
     Italijani
    -0.66
    Personensuche
    -0.65
    Jeografia
    -0.65
     nawr
    -0.62
    POSITIVE LOGITS
     shenan
    1.59
     maneu
    1.48
     apprehen
    1.47
     depic
    1.43
     pamph
    1.42
     accla
    1.42
     reluct
    1.38
     milf
    1.37
     cuck
    1.35
     sophistic
    1.34
    Activations Density 0.246%

    No Known Activations