© 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. 7529
    Prev
    Next
    INDEX
    Explanations

    phrases related to childhood experiences, trauma, and overcoming challenges

    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
    674
    +0.14
    0.4%
    1013
    +0.09
    0.3%
    1042
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.14
    0.02
    177
    +0.09
    0.03
    297
    +0.08
    0.04
    Negative Logits
     heapq
    -0.86
     smtplib
    -0.81
     pymysql
    -0.81
    Glej
    -0.72
     psycopg
    -0.69
    Sklici
    -0.69
     pymongo
    -0.63
     hashlib
    -0.59
    HideInInspector
    -0.57
    Zunanje
    -0.54
    POSITIVE LOGITS
     incess
    0.88
     trico
    0.88
     tille
    0.85
     marte
    0.82
     ordina
    0.82
     velours
    0.81
     monaster
    0.79
     cannes
    0.79
     aquare
    0.79
     tyn
    0.78
    Activations Density 0.182%

    No Known Activations