© 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. 896
    Prev
    Next
    INDEX
    Explanations

    functions and code snippets related to memory management in programming languages

    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
    876
    +0.16
    0.5%
    1699
    +0.11
    0.3%
    674
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    769
    +0.16
    0.01
    876
    +0.11
    0.00
    1216
    +0.11
    0.01
    Negative Logits
    cedula
    -0.64
    Precis
    -0.57
    Hochspringen
    -0.56
    departamento
    -0.55
    لقد
    -0.54
    Quem
    -0.54
    ejercicio
    -0.54
     Muzeum
    -0.54
    llave
    -0.54
     once
    -0.53
    POSITIVE LOGITS
     !...
    1.51
     ?...
    1.47
     :)))
    1.46
     coq
    1.41
     fluo
    1.41
     bordeaux
    1.35
     peppa
    1.35
     emphat
    1.33
     haup
    1.31
     nutella
    1.27
    Activations Density 0.039%

    No Known Activations