© 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. 13916
    Prev
    Next
    INDEX
    Explanations

    adjectives reflecting emotions or personal qualities

    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
    198
    +0.13
    0.4%
    1385
    +0.11
    0.3%
    946
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.13
    0.06
    802
    +0.11
    0.06
    260
    +0.11
    0.04
    Negative Logits
     duomen
    -0.53
    PointSize
    -0.53
    maxWidth
    -0.52
    ]**
    -0.52
    setLayout
    -0.51
    dhism
    -0.50
    )>>
    -0.50
    fillStyle
    -0.50
    PCell
    -0.50
    )>=
    -0.50
    POSITIVE LOGITS
     mef
    0.88
     triton
    0.86
     uncin
    0.85
     pubg
    0.84
     Juf
    0.82
     passim
    0.81
     casio
    0.80
     Augu
    0.80
     Khart
    0.79
     logitech
    0.79
    Activations Density 0.343%

    No Known Activations