© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7639
    Prev
    Next
    INDEX
    Explanations

    phrases related to innovation, technology advancements, and pushing boundaries

    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
    872
    +0.10
    0.3%
    584
    +0.07
    0.2%
    1554
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    781
    +0.10
    0.03
    1028
    +0.07
    0.04
    787
    +0.07
    0.03
    Negative Logits
     shenan
    -0.67
     apprehen
    -0.67
     accla
    -0.61
     intersper
    -0.60
     affor
    -0.59
     vagu
    -0.58
     philanth
    -0.57
     depic
    -0.57
     encomp
    -0.55
     maneu
    -0.55
    POSITIVE LOGITS
     boundaries
    0.77
     assumptions
    0.63
    boundaries
    0.60
     conventional
    0.59
     paradigms
    0.58
     conventions
    0.58
     Boundaries
    0.57
     distanciation
    0.56
    ioneers
    0.56
     paradigma
    0.55
    Activations Density 0.366%

    No Known Activations