© 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. 14140
    Prev
    Next
    INDEX
    Explanations

    personal reflections and introspections, possibly related to self-awareness and relationships with others

    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
    50
    +0.12
    0.4%
    2015
    +0.12
    0.4%
    381
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1959
    +0.12
    0.09
    163
    +0.12
    0.02
    2015
    +0.10
    -0.01
    Negative Logits
     dises
    -1.13
     susun
    -1.08
     magis
    -1.06
     robus
    -1.04
     palab
    -1.03
     kosme
    -1.00
     fono
    -1.00
     hcm
    -0.99
     hina
    -0.99
     permu
    -0.98
    POSITIVE LOGITS
     my
    0.77
     I
    0.69
     myself
    0.65
     me
    0.60
     ungrateful
    0.56
     someday
    0.55
     hurtful
    0.53
     mine
    0.53
    <eos>
    0.52
    I
    0.52
    Activations Density 0.976%

    No Known Activations