© 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. 13854
    Prev
    Next
    INDEX
    Explanations

    positive descriptions or evaluations

    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
    122
    +0.16
    0.6%
    553
    +0.13
    0.5%
    1416
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.16
    0.03
    197
    +0.13
    0.02
    1512
    +0.12
    0.02
    Negative Logits
     purcha
    -0.95
     affor
    -0.94
     depic
    -0.94
     increa
    -0.92
     indestru
    -0.91
     apprehen
    -0.90
     unden
    -0.89
     beaute
    -0.86
     encomp
    -0.85
     paula
    -0.84
    POSITIVE LOGITS
     bright
    1.35
    bright
    1.30
     Bright
    1.25
    Bright
    1.19
    BRIGHT
    1.13
     brighter
    1.13
     brightness
    1.08
     brightest
    1.08
     BRIGHT
    1.04
     brighten
    0.90
    Activations Density 0.068%

    No Known Activations